diff --git a/pydata-eindhoven-2020/category.json b/pydata-eindhoven-2020/category.json
new file mode 100644
index 000000000..982682eaf
--- /dev/null
+++ b/pydata-eindhoven-2020/category.json
@@ -0,0 +1,3 @@
+{
+  "title": "PyData Eindhoven 2020"
+}
diff --git a/pydata-eindhoven-2020/videos/adam-grzywaczewski-rapids-how-to-accelerate-your-data-science-pipeline-by-orders-of-magnitude.json b/pydata-eindhoven-2020/videos/adam-grzywaczewski-rapids-how-to-accelerate-your-data-science-pipeline-by-orders-of-magnitude.json
new file mode 100644
index 000000000..52b5ba837
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/adam-grzywaczewski-rapids-how-to-accelerate-your-data-science-pipeline-by-orders-of-magnitude.json
@@ -0,0 +1,28 @@
+{
+  "description": "PyData Eindhoven 2020\n\nThis talk will discuss the RAPIDS suite of open source software libraries which give you the ability to execute end-to-end data science and analytics pipelines entirely on GPUs. Because its API was deliberately designed to be consistent with existing data science utilities (e.g. Pandas DataFrame, SciKit Learn) its integration in majority of cases is limited to only several lines of code change.\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 2014,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Adam Grzywaczewski"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/6XzS5XcpicM/maxresdefault.webp",
+  "title": "RAPIDS: How to accelerate your data science pipeline by orders of magnitude",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=6XzS5XcpicM"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/avik-sengupta-productivity-and-performance-in-one-programming-language-a-tour-of-julia.json b/pydata-eindhoven-2020/videos/avik-sengupta-productivity-and-performance-in-one-programming-language-a-tour-of-julia.json
new file mode 100644
index 000000000..91bf80b65
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/avik-sengupta-productivity-and-performance-in-one-programming-language-a-tour-of-julia.json
@@ -0,0 +1,28 @@
+{
+  "description": "PyData Eindhoven 2020\n\nThis talk answers the question: What makes Julia unique? We explore the design innovations that make Julia stand out from other languages of its generation. We discuss areas where it matters, and how it helps programmers in a wide range of domains. We will see examples of these features making a difference in real life use cases, from finance to biotech to scientific machine learning.\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1775,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Avik Sengupta"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/tkK4zhuAJms/maxresdefault.webp",
+  "title": "Productivity and performance in one programming language - A tour of Julia",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=tkK4zhuAJms"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/corinne-vigreux-interview-about-codam-coding-college-pydata-eindhoven-2020.json b/pydata-eindhoven-2020/videos/corinne-vigreux-interview-about-codam-coding-college-pydata-eindhoven-2020.json
new file mode 100644
index 000000000..3789c7e17
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/corinne-vigreux-interview-about-codam-coding-college-pydata-eindhoven-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "www.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1713,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Corinne Vigreux"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/zAs8EMmvG94/maxresdefault.webp",
+  "title": "Interview about Codam Coding College",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=zAs8EMmvG94"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/daan-de-bruin-fighting-covid-with-python-pydata-eindhoven-2021.json b/pydata-eindhoven-2020/videos/daan-de-bruin-fighting-covid-with-python-pydata-eindhoven-2021.json
new file mode 100644
index 000000000..f7269b888
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/daan-de-bruin-fighting-covid-with-python-pydata-eindhoven-2021.json
@@ -0,0 +1,28 @@
+{
+  "description": "www.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 2055,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Daan de Bruin"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/yhrPTiN7Cjw/maxresdefault.webp",
+  "title": "Fighting COVID with Python",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=yhrPTiN7Cjw"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/damiaan-zwietering-building-a-coronaradar-pydata-eindhoven-2020.json b/pydata-eindhoven-2020/videos/damiaan-zwietering-building-a-coronaradar-pydata-eindhoven-2020.json
new file mode 100644
index 000000000..786dbb28d
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/damiaan-zwietering-building-a-coronaradar-pydata-eindhoven-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Having extensive data mining experience but limited Python knowledge I fired up a notebook and started digging into COVID case data from EU CDC. A couple of months later, after visualization, curve fitting, modeling and mapping I developed a coronaradar showing and projecting the spread of infections across the world. Let's have a look together at what I did, no slides, just live code.\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 3922,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Damiaan Zwietering"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/pW-YYRNeyhA/maxresdefault.webp",
+  "title": "Building a coronaradar",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=pW-YYRNeyhA"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/damian-andrew-tamburri-radon-devops-framework-to-optimally-exploit-serverless-computing-tech.json b/pydata-eindhoven-2020/videos/damian-andrew-tamburri-radon-devops-framework-to-optimally-exploit-serverless-computing-tech.json
new file mode 100644
index 000000000..520d203bf
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/damian-andrew-tamburri-radon-devops-framework-to-optimally-exploit-serverless-computing-tech.json
@@ -0,0 +1,28 @@
+{
+  "description": "RADON: DevOps framework to optimally exploit serverless computing technologies\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 2076,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Damian Andrew Tamburri"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/Jl2s9Emf5JI/maxresdefault.webp",
+  "title": "RADON: DevOps framework to optimally exploit serverless computing technologies",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=Jl2s9Emf5JI"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/daniel-lee-stan-why-does-it-exist-when-is-it-useful-why-do-i-use-it-pydata-eindhoven-2020.json b/pydata-eindhoven-2020/videos/daniel-lee-stan-why-does-it-exist-when-is-it-useful-why-do-i-use-it-pydata-eindhoven-2020.json
new file mode 100644
index 000000000..9431f8ec6
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/daniel-lee-stan-why-does-it-exist-when-is-it-useful-why-do-i-use-it-pydata-eindhoven-2020.json
@@ -0,0 +1,32 @@
+{
+  "description": "Stan (https://mc-stan.org) is one of the most popular probabilistic programming languages. This talk will be a high-level talk covering 3 things: why Stan exists, when it's useful, and why I use it (with an example).\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1699,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://mc-stan.org",
+      "url": "https://mc-stan.org"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Daniel Lee"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/SBmqnd1W_iA/maxresdefault.webp",
+  "title": "Stan: why does it exist? when is it useful? why do I use it?",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=SBmqnd1W_iA"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/dennis-ramondt-monitoring-a-tv-streaming-service-with-ai-from-pagerank-to-graph-convolutions.json b/pydata-eindhoven-2020/videos/dennis-ramondt-monitoring-a-tv-streaming-service-with-ai-from-pagerank-to-graph-convolutions.json
new file mode 100644
index 000000000..a713daf1a
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/dennis-ramondt-monitoring-a-tv-streaming-service-with-ai-from-pagerank-to-graph-convolutions.json
@@ -0,0 +1,28 @@
+{
+  "description": "PyData Eindhoven 2020\n\nLiberty Global's digital TV platform is a complex graph-based IT system that needs to be constantly monitored to prevent downtime. Anomaly detection and graph analytics support engineers with timely problem identification. We show how we evolve graph deep learning methods such as node embedding and message passing from unsupervised to semi-supervised as root causes are gradually being labeled.\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1981,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Dennis Ramondt"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/_Avui3hkOVA/maxresdefault.webp",
+  "title": "Monitoring a TV streaming service with AI - from PageRank to graph convolutions",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=_Avui3hkOVA"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/dr-ir-e-taskesen-improving-the-data-understanding-part-by-graphical-hypergeometric-networks.json b/pydata-eindhoven-2020/videos/dr-ir-e-taskesen-improving-the-data-understanding-part-by-graphical-hypergeometric-networks.json
new file mode 100644
index 000000000..ccf9f29ba
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/dr-ir-e-taskesen-improving-the-data-understanding-part-by-graphical-hypergeometric-networks.json
@@ -0,0 +1,28 @@
+{
+  "description": "PyData Eindhoven 2021\n\nA challenge in real-world data is, among others, the data understanding part. We propose graphical hypergeometric networks (HNet), a method where associations across variables are tested for significance by statistical inference. HNet learns the Association from datasets with mixed datatypes and with unknown function.\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 2021,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "E. Taskesen"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/0TXdnSPSzZ4/maxresdefault.webp",
+  "title": "Improving the data understanding part by graphical hypergeometric networks",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=0TXdnSPSzZ4"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/ilias-sarantopoulos-real-time-ml-services-from-ideation-to-production-pydata-eindhoven-2020.json b/pydata-eindhoven-2020/videos/ilias-sarantopoulos-real-time-ml-services-from-ideation-to-production-pydata-eindhoven-2020.json
new file mode 100644
index 000000000..d79aae939
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/ilias-sarantopoulos-real-time-ml-services-from-ideation-to-production-pydata-eindhoven-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "In this presentation, we are going to talk about how we tackle the problem of forecasting time series data for our Real Time Dynamic Pricing service and the challenges we have faced putting into production a real time streaming ML service while adopting an MLOps lifecycle.\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1805,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Ilias Sarantopoulos"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/fOYSk702AHc/maxresdefault.webp",
+  "title": "Real-Time ML services: From ideation to production",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=fOYSk702AHc"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/koen-vossen-from-notebook-to-production-using-flask-and-heroku-pydata-eindhoven-2020.json b/pydata-eindhoven-2020/videos/koen-vossen-from-notebook-to-production-using-flask-and-heroku-pydata-eindhoven-2020.json
new file mode 100644
index 000000000..4d529c34b
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/koen-vossen-from-notebook-to-production-using-flask-and-heroku-pydata-eindhoven-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Learn from a developers perspective how to go from a notebook to production. In this talk we will provide an overview of the steps required to go from code in a notebook to an application running in production.\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 3598,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Koen Vossen"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/BobaHtafXm0/maxresdefault.webp",
+  "title": "From notebook to production using flask and heroku",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=BobaHtafXm0"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/matthew-rocklin-dask-at-global-scale-with-coiled-pydata-eindhoven-2020.json b/pydata-eindhoven-2020/videos/matthew-rocklin-dask-at-global-scale-with-coiled-pydata-eindhoven-2020.json
new file mode 100644
index 000000000..b358bd09a
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/matthew-rocklin-dask-at-global-scale-with-coiled-pydata-eindhoven-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Dask developers joined with Python web developers to make Coiled, a global scale service providing managed Dask to everyone, everywhere. This talk describes some of our design constraints, a bit of the architecture, and then goes into examples of what this enables across different parts of the PyData community.\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1873,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Matthew Rocklin"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/gkUSDe4rETE/maxresdefault.webp",
+  "title": "Dask at Global Scale with Coiled",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=gkUSDe4rETE"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/matthijs-brouns-10x-smaller-docker-containers-for-data-science-pydata-eindhoven-2020.json b/pydata-eindhoven-2020/videos/matthijs-brouns-10x-smaller-docker-containers-for-data-science-pydata-eindhoven-2020.json
new file mode 100644
index 000000000..a3e0a0da4
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/matthijs-brouns-10x-smaller-docker-containers-for-data-science-pydata-eindhoven-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "If you work with Docker on a regular basis you've probably been told that you should try to keep your container images small. We generally prefer smaller images because they upload faster and take up less disk space.\n\nIn this talk we'll try to build the smallest possible docker image, containing a basic PyData tools stack that includes Matplotlib, Scipy, Numpy and Scikit-learn.\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1904,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Matthijs Brouns"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/Z1Al4I4Os_A/maxresdefault.webp",
+  "title": "10x smaller docker containers for Data Science",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=Z1Al4I4Os_A"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/nicola-pezzotti-artificial-intelligence-to-accelerate-mri-scans-philips-lumc-winners-in-the.json b/pydata-eindhoven-2020/videos/nicola-pezzotti-artificial-intelligence-to-accelerate-mri-scans-philips-lumc-winners-in-the.json
new file mode 100644
index 000000000..40b67c9b1
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/nicola-pezzotti-artificial-intelligence-to-accelerate-mri-scans-philips-lumc-winners-in-the.json
@@ -0,0 +1,28 @@
+{
+  "description": "Artificial intelligence to accelerate MRI scans - Philips & LUMC winners in the fastMRI challenge\n\nPhilips succesfully participated in the first fastMRI challenge, a competition organized by NYU Langone Health and Facebook AI Resarch, to demonstrate how artificial intellignce can accelerate MRI scanners. In the talk, I will introduce the challenge and the problem, present the winning solution developed by the Philips & LUMC team and the challenge results.\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 2040,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Nicola Pezzotti"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/5EcfIVbkOiQ/maxresdefault.webp",
+  "title": "Artificial intelligence to accelerate MRI scans",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=5EcfIVbkOiQ"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/nikki-van-ommeren-maike-fischer-productionizing-an-unsupervised-machine-learning-model-to.json b/pydata-eindhoven-2020/videos/nikki-van-ommeren-maike-fischer-productionizing-an-unsupervised-machine-learning-model-to.json
new file mode 100644
index 000000000..5108ab652
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/nikki-van-ommeren-maike-fischer-productionizing-an-unsupervised-machine-learning-model-to.json
@@ -0,0 +1,29 @@
+{
+  "description": "Productionizing an unsupervised machine learning model to understand customer feedback\n\nHave you ever had to read through over 5,000 open-text feedback responses a month?\n\nOur colleagues at ING do this all the time, spending multiple hours each week. This is why we developed an unsupervised machine learning model that clusters customer feedback with similar meaning using open-source Python libraries.\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1774,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Nikki van Ommeren",
+    "Maike Fischer"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/YLTLdEiJcq0/maxresdefault.webp",
+  "title": "Productionizing an unsupervised machine learning model to understand customer feedback",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=YLTLdEiJcq0"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/reza-sahraeian-the-industrial-challenge-of-missing-data-pydata-eindhoven-2020.json b/pydata-eindhoven-2020/videos/reza-sahraeian-the-industrial-challenge-of-missing-data-pydata-eindhoven-2020.json
new file mode 100644
index 000000000..5ce57dc13
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/reza-sahraeian-the-industrial-challenge-of-missing-data-pydata-eindhoven-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Missing data is a common problem in many application. This talk aims at providing a brief overview on the origin of data missingness as well as covering effective approaches to handle that via some practical examples showing how to use and implement missing data techniques using open source python libraries. This talk suits data and machine learning scientists both in industry and academy.\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1584,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Reza Sahraeian"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/M4CtBKrp59w/maxresdefault.webp",
+  "title": "The industrial challenge of missing data",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=M4CtBKrp59w"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/ruben-mak-the-causal-problem-of-overexposure-to-repetitive-ads-instrument-variables-and-pymc3.json b/pydata-eindhoven-2020/videos/ruben-mak-the-causal-problem-of-overexposure-to-repetitive-ads-instrument-variables-and-pymc3.json
new file mode 100644
index 000000000..8a8ea1037
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/ruben-mak-the-causal-problem-of-overexposure-to-repetitive-ads-instrument-variables-and-pymc3.json
@@ -0,0 +1,28 @@
+{
+  "description": "PyData Eindhoven 2020\n\nRise of the internet has created opportunities to specifically target consumers. Counterintuitively, this has resulted in overexposure of users to repetitive ads. In this talk, I will show why this is a result of causality problems using a case study. I will demonstrate how we apply instrumental variables and pymc3 to solve these problems.\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1045,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Ruben Mak"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/28QsFSAKyKM/maxresdefault.webp",
+  "title": "The causal problem of overexposure to repetitive ads: instrument variables and pymc3",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=28QsFSAKyKM"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/sundas-khalid-bias-in-data-pydata-eindhoven-2020.json b/pydata-eindhoven-2020/videos/sundas-khalid-bias-in-data-pydata-eindhoven-2020.json
new file mode 100644
index 000000000..07fd2bac4
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/sundas-khalid-bias-in-data-pydata-eindhoven-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "www.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1483,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Sundas Khalid"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/TjLtIDDK3sg/maxresdefault.webp",
+  "title": "Bias in Data",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=TjLtIDDK3sg"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/vincent-warmerdam-playing-by-the-rules-based-systems-pydata-eindhoven-2020.json b/pydata-eindhoven-2020/videos/vincent-warmerdam-playing-by-the-rules-based-systems-pydata-eindhoven-2020.json
new file mode 100644
index 000000000..4064616be
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/vincent-warmerdam-playing-by-the-rules-based-systems-pydata-eindhoven-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "Back in the old days, it was common to write rule-based systems. Systems that do; data - [rules] -labels.\n\nNowadays, it's much more fashionable to use machine learning instead. Something like; (labels, data) - [model] - rules.\n\nIt might be a good time to ask ourselves, is this a better approach? Or have we lost something while in this transition?\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 2278,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Vincent Warmerdam"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/nJAmN6gWdK8/maxresdefault.webp",
+  "title": "Playing by the Rules-Based-Systems",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=nJAmN6gWdK8"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/vladimir-osin-understanding-deep-neural-networks-pydata-eindhoven-2020.json b/pydata-eindhoven-2020/videos/vladimir-osin-understanding-deep-neural-networks-pydata-eindhoven-2020.json
new file mode 100644
index 000000000..51e5be321
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/vladimir-osin-understanding-deep-neural-networks-pydata-eindhoven-2020.json
@@ -0,0 +1,28 @@
+{
+  "description": "As deep learning practitioners, we would like to know what input features are responsible for our model decision and start treating our models as white boxes. In the literature, this problem is known as attribution. During this talk, we discuss this problem and several available solutions that you can start using already now in PyTorch ecosystem.\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1628,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Vladimir Osin"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/VLTiFtKONlI/maxresdefault.webp",
+  "title": "Understanding Deep Neural Networks",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=VLTiFtKONlI"
+    }
+  ]
+}
diff --git a/pydata-eindhoven-2020/videos/wilder-rodrigues-applying-deep-learning-for-object-detection-from-a-telecom-perspective.json b/pydata-eindhoven-2020/videos/wilder-rodrigues-applying-deep-learning-for-object-detection-from-a-telecom-perspective.json
new file mode 100644
index 000000000..ecd74eed7
--- /dev/null
+++ b/pydata-eindhoven-2020/videos/wilder-rodrigues-applying-deep-learning-for-object-detection-from-a-telecom-perspective.json
@@ -0,0 +1,28 @@
+{
+  "description": "PyData Eindhoven 2020\n\nAiming at improving our Net Promoter Score by providing better assistance to our customers and, at the same time, reducing calls and truck rolls, VodafoneZiggo applies Computer Vision to help customers identify their in-home setup. In this talk, we will cover the challenges faced with data collection, our struggles with labelling platforms and how we automated our pipelines.\n\n===\nwww.pydata.org\r\n\r\nPyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. \r\n\r\nPyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!\n00:10 Help us add time stamps or captions to this video! See the description for details.\n\nWant to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps",
+  "duration": 1897,
+  "language": "eng",
+  "recorded": "2020-10-07",
+  "related_urls": [
+    {
+      "label": "Conference Website",
+      "url": "https://pydata.org/eindhoven2020/schedule/"
+    },
+    {
+      "label": "https://github.com/numfocus/YouTubeVideoTimestamps",
+      "url": "https://github.com/numfocus/YouTubeVideoTimestamps"
+    }
+  ],
+  "speakers": [
+    "Wilder Rodrigues"
+  ],
+  "tags": [],
+  "thumbnail_url": "https://i.ytimg.com/vi_webp/I-AuUDaWw4k/maxresdefault.webp",
+  "title": "Applying Deep Learning for Object Detection from a Telecom Perspective",
+  "videos": [
+    {
+      "type": "youtube",
+      "url": "https://www.youtube.com/watch?v=I-AuUDaWw4k"
+    }
+  ]
+}