AI Essentials

Research

Discover how AI, Machine Learning and advanced algorithms impact our lives, our jobs and the economy thanks to expert articles that include discussion on the potential, limits and consequences of AI

AI Essentials

Top news of the week: 28.10.2021.

Machine learning
Reinforcement learning
Neural network
Gradient
Frequency domain
Electrical engineering

Research

@weballergy shared
On Oct 25, 2021
RT @hardmaru: Under the right conditions, an unsupervised neural net absorbing a sufficient amount of diversified experiences may lead to a general understanding of its data, meta-learning, and perhaps even a consciousness to emerge! Fascinating article by @ericjang11. https://t.co/xzjeakmSgb
Open
Just Ask for Generalization

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 ...

@hardmaru shared
On Oct 27, 2021
Parameter Prediction for Unseen Deep Architectures Their graph hypernetwork can predict all 24M parameters of a ResNet-50, achieving 60% CIFAR-10 accuracy, and 50% Top-5 accuracy on ImageNet. A forward pass takes only a fraction of a second, even on a CPU!https://t.co/qRJiDTVRoH
Open
Parameter Prediction for Unseen Deep Architectures

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 ...

@stanfordnlp shared
On Oct 27, 2021
At our next @stanfordnlp seminar, Tom Hope from @ai2_allennlp/@uwnlp tells us about harnessing scientific literature for boosting discovery and innovation. It is at 11 am PT tomorrow and open to public: details - https://t.co/R2UMRaVQp5, registration - https://t.co/yghoh9KCNj https://t.co/lCrxEsgwZ0
Open
The Stanford Natural Language Processing Group

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, …

@hardmaru shared
On Oct 27, 2021
RT @tyrell_turing: Our two spotlight papers (by @ShahabBakht and @patrickmineault) at #NeurIPS2021 showing how ANNs can develop dorsal stream representations now have their websites up (with links to the updated papers and code): https://t.co/ACz0tmEsJV https://t.co/T7zLzBUhcD
Open
The functional specialization of visual cortex emerges from training parallel pathways with self-supervised predictive learning

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 …

@NandoDF shared
On Oct 26, 2021
RT @svlevine: I wrote a little position paper about how unsupervised RL methods could provide a powerful framework for self-supervised learning. This will appear in the inaugural CoRL Blue Sky Track: https://t.co/lrQeHe7XOG Condensed online version (w/ animations!): https://t.co/qJcfI2MKwZ
Open
Understanding the World Through Action

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 ...

@stanfordnlp shared
On Oct 26, 2021
RT @AmazonScience: Earlier this month Amazon hosted its 9th internal machine learning conference, which featured presentations from prominent computer science professors Joshua Bengio, Rama Chellappa, @tdietterich, Mirella Lapata, and @chrmanning. Watch the videos. #ML https://t.co/LaLH9Mgmmn
Open
Amazon's annual machine learning conference featured presentations from thought leaders within academia

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.

@NandoDF shared
On Oct 26, 2021
RT @instadeepai: InstaDeep is pleased to organize a session on "Playing Starcraft and Saving the World Using MARL" as part of IndabaX South Africa 2021, happening online on 29 Oct, 2 to 4pm SAST Read event details https://t.co/xLifzrGMrX Registration link https://t.co/8GoGodri5g @DeepIndabaX_ZA https://t.co/jnXyN2aNT1
Open
IndabaX South Africa – Using MARL to Play StarCraft II

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 ...

@WIREDScience shared
On Oct 24, 2021
Built upon the ubiquitous Fourier transform, these mathematical tools allow unprecedented analysis of continuous signals. https://t.co/4ZURXtjrFf
Open
How Wavelets Let Researchers Transform and Understand Data

How Wavelets Let Researchers Transform and Understand Data

Built upon the ubiquitous Fourier transform, these mathematical tools allow unprecedented analysis of continuous signals.

Read more: Research
weekly 28.10.2021
View archives
Back to home

Subscribe to AI Essentials - Research.

Avoid an information overload and get the most trusted industry news hand-picked by the top Experts. Sign up for the weekly AI Essentials - Research.
Privacy Policy

Sign up for the weekly AI Essentials - Research newsletter

Never again miss anything or anyone that matter in AI Essentials

Sign up and receive the AI Essentials - Research weekly email newsletter directly to your inbox. Make more informed business decisions based on insight for the most trusted industry experts, faster.
Privacy Policy