This archive holds videos of past Fields lectures. Lectures are archived in two formats.The interactive format, viewed in a flash-player-enabled desktop web browser, allows you to zoom in and out on specific areas of the blackboards or screens (providing a viewing experience more like being present in the room). The static format, although it does not allow for zooming in to read small blackboard writing, is downloadable and compatible with a wide variety of desktop and mobile video players.
This is the Graph Neural Networks: Hands-on Session from the Stanford 2019 Fall CS224W course.
In this tutorial, we will explore the implementation of graph neural networks and investigate what representations these networks learn. Along the way, we'll see how PyTorch Geometric and TensorBoardX can help us with constructing and training graph models.
Pytorch Geometric tutorial part starts at -- 0:33:30
Details on:
* Graph Convolutional Neural Networks (GCN)
* Custom Convolutional Model
* Message passing
* Aggregation functions
* Update
* Graph Pooling
Physics is a part of games that has always amazed me. I find it funny how impossible it seemed to do correctly when I was younger. While making a custom game engine, it was finally demystified!
The full article: https://blog.winter.dev/2020/designing-a-physics-engine/
The background game demo: https://winter.dev/demo
What if there was an Empire-focussed short Star Wars animation, drawn with the crazy detail and shading of classic 80s anime that's all but vanished from Japan nowadays? Well, I tried my best.
The textbook Analytic Combinatorics by Philippe Flajolet and Robert Sedgewick enables precise quantitative predictions of the properties of large combinatorial structures.
Karan Thapar speaks to former Pakistani ambassador to the US and well-known academic scholar Husain Haqqani about his new book 'Reimagining Pakistan: Transfo...
The center of the technology world may not lie in California's Silicon Valley, but in the bustling marketplace of Huaqiangbei, a subdistrict of Shenzhen...
Solving a 5 yr old personal mystery about "Why Water Walks on Water". Click here to tweet this video: https://goo.gl/oYRa57 Thanks to Google Making & Science...
The PUNLAG seminar is intended to supplement the numerical linear algebra course sequence at Purdue. The standard course CS515 doesn't have room for a number of interesting problems -- we hope to cover some in this seminar!
Use a computer? Game on a PC? Ever wonder how those graphics get so pretty? Let's go inside your high-end graphics card with this animation. Subscribe for mo...
Basic principle and practical procedure of the tensile test on ductile metallic materials - Testing machine (Inspekt 200 kN, Hegewald & Peschke Meß- und Prüf...
This course will introduce the student to classic neural network structures, Convolution Neural Networks (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Neural Networks (GRU), General Adversarial Networks (GAN) and reinforcement learning. Application of these architectures to computer vision, time series, security, natural language processing (NLP), and data generation will be covered. High Performance Computing (HPC) aspects will demonstrate how deep learning can be leveraged both on graphical processing units (GPUs), as well as grids. Focus is primarily upon the application of deep learning to problems, with some introduction to mathematical foundations. Students will use the Python programming language to implement deep learning using Google TensorFlow and Keras.
Spinning objects have strange instabilities known as The Dzhanibekov Effect or Tennis Racket Theorem - this video offers an intuitive explanation. Part of th...