|April 10 · Issue #104 · View online |
If there’s anything you think we missed or want to see in next week’s issue, send us a note on Twitter: @dl_weekly
Until next week!
| Facebook’s AI is helping deliver health care and electricity to unmapped regions - MIT Technology Review |
Facebook has combined satellite images and deep learning to create a new population density map for the majority of Africa, which the company released April 9th.
| Google cancels AI ethics board in response to outcry - Vox |
Google’s latest attempt to oversee “responsible AI development” failed before it got off the ground. The entire ethics board has been scrapped following backlash over the nominations of multiple problematic members.
| Apple hires Google AI expert Ian Goodfellow to direct machine learning | VentureBeat |
Apple has hired GAN pioneer, Ian Goodfellow, from Google to direct machine learning.
| The Animal-AI Olympics is going to treat AI like a lab rat - MIT Technology Review |
The $10,000 competition will test AI with challenges that were originally designed to test animal cognition—to see how close we are to machines that have common sense.
| The basics of modern AI—how does it work and will it destroy society this year? | Ars Technica |
A nice primer on what people mean when they use the term “AI” these days.
| CS230 Deep Learning |
Deep Learning is one of the most highly sought after skills in AI. In this course, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more.
| Which GPU(s) to Get for Deep Learning: My Experience and Advice for Using GPUs in Deep Learning |
You want a cheap high performance GPU for deep learning? This blog post guides you through the choices, so you can find the GPU that’s best for you. The RTX 2070 comes out ahead.
| Open-sourcing PyTorch-BigGraph for faster embeddings of extremely large graphs |
Facebook AI has created and is now open-sourcing PyTorch-BigGraph (PBG), a tool that makes it much faster and easier to produce graph embeddings for…
| GitHub - LynnHo/DCGAN-LSGAN-WGAN-GP-DRAGAN-TensorFlow-2: DCGAN LSGAN WGAN-GP DRAGAN TensorFlow 2 |
A bunch of GANs implemented in TensorFlow 2.
| [1904.02632] A Learned Representation for Scalable Vector Graphics |
Abstract: Dramatic advances in generative models have resulted in near photographic quality for artificially rendered faces, animals and other objects in the natural world. In spite of such advances, a higher level understanding of vision and imagery does not arise from exhaustively modeling an object, but instead identifying higher-level attributes that best summarize the aspects of an object. In this work we attempt to model the drawing process of fonts by building sequential generative models of vector graphics. This model has the benefit of providing a scale-invariant representation for imagery whose latent representation may be systematically manipulated and exploited to perform style propagation.“
This summary has been corrected from a previous version.
| [1903.06874] Fast Interactive Object Annotation with Curve-GCN |
Abstract: “Manually labeling objects by tracing their boundaries is a laborious process. In Polygon-RNN++ the authors proposed Polygon-RNN that produces polygonal annotations in a recurrent manner using a CNN-RNN architecture, allowing interactive correction via humans-in-the-loop. We propose a new framework that alleviates the sequential nature of Polygon-RNN, by predicting all vertices simultaneously using a Graph Convolutional Network (GCN). Our model is trained end-to-end. It supports object annotation by either polygons or splines, facilitating labeling efficiency for both line-based and curved objects.”