Biological and artificial intelligence commentary on this blog post by Surya Ganguli I wanted to provide some commentary on this blog post by Surya Ganguli, which appeared on December 5th 2...

Predictive neural networks for reinforcement learning Ingredients: Visual network: a CNN encoder (CNN1) or similar that takes the visual input (raw pixels) and provides embedding e_t (a vec...

Learning and performing in the real world — part 2 We have argued for the need to use predictive neural network to improve the learning abilities and speed of reinforcement learning algorithms — s...

Continual learning How to keep learning without forgetting By Eugenio Culurciello and Vincenzo Lomonaco Today we mostly train neural network based on fixed pre-determined datasets. This gives ve...

29,000 days An average human life is about 80 years, or some 29,000 days. When we were young we never though so much of it. We knew our time on this planet was limited, but we were more interest...

Learning neural network architectures how to automatically create neural networks Last time we talked about the limits of learning and how eliminating the need for design of neural network arch...

At the limits of learning Deep learning success lies with the promises of neural networks being able to learn from data. This is in contrast with the way we designed and tested algorithms before...

Analysis of deep neural networks for pixel processing — part One By Dawood Sheik, Abhishek Chaurasia, Eugenio Culurciello We measured the performance of the following bounding box detectors on...

Analysis of deep neural networks By Alfredo Canziani, Thomas Molnar, Lukasz Burzawa, Dawood Sheik, Abhishek Chaurasia, Eugenio Culurciello This are updated figure from the paper: An Analysis of...

Notes on Transformer neural network for sequence to sequence learning This post are notes to understand sequence-to-sequence (s2s) neural networks and in particular the Transformer neural network...