Top news of the week: 28.10.2021.
Research
Just Ask for Generalization
This blog post outlines a key engineering principle I’ve come to believe strongly in for building general AI systems with deep learning. This principle guides my present-day research tastes ...
Parameter Prediction for Unseen Deep Architectures
Deep learning has been successful in automating the design of features in machine learning pipelines. However, the algorithms optimizing neural network parameters remain largely ...
The Stanford Natural Language Processing Group
Harnessing Scientific Literature for Boosting Discovery and Innovation Tom Hope, Allen Institute for AI, Univ. of Washington Venue: Zoom (link hidden) Abstract In the year 1665, …
The functional specialization of visual cortex emerges from training parallel pathways with self-supervised predictive learning
These two pathways support behaviours related to visual recognition and movement, respectively. We explore this question using data from mice, who like other mammals, have …
Understanding the World Through Action
The recent history of machine learning research has taught us that machine learning methods can be most effective when they are provided with very large, high-capacity models, and trained ...
Amazon's annual machine learning conference featured presentations from thought leaders within academia
Amazon Machine Learning Conference highlights use of machine learning across the company’s businesses and its increasing value to customers.
IndabaX South Africa – Using MARL to Play StarCraft II
Continuing the company’s commitment to supporting and building the AI and ML community across Africa following the highly successful IndabaX Tunisia, InstaDeep is also organizing a session ...
How Wavelets Let Researchers Transform and Understand Data
Built upon the ubiquitous Fourier transform, these mathematical tools allow unprecedented analysis of continuous signals.