nature
A neural network trained for prediction mimics diverse features of biological neurons and perception
· The deep convolutional recurrent neural network ‘PredNet’ can be trained to predict future video frames in a self-supervised manner. A surprising result is that it captures a wide array of phenomena observed in natural neuronal systems, ranging from low-level visual cortical neuron response properties to high-level perceptual illusions, hinting at potential similarities between recurrent predictive neural network models and computations in the brain. · Shared by 5, including Matt Shaffer
AI Papers
Stability-Guaranteed Reinforcement Learning for Contact-rich Manipulation
1 min · · Reinforcement learning (RL) has had its fair share of success in contact-rich manipulation tasks but it still lags behind in benefiting from advances in robot control theory such as impedance control… · Shared by 6, including Matt Shaffer
shortscience.org
Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
2 min · · disclaimer: I'm the first author of the paper ## TL;DR We have made a lot of progress on catastrophic forgetting within the standard evaluation protocol, i.e. sequentially learning a stream of tasks… · Shared by 5, including Matt Shaffer