This is a ~weekly Link Roundup of the most interesting content I found in the past week.
News and Resources for Artificial Intelligence and Neuroscience.
Deep reinforcement learning methods attain super-human performance in a wide range of environments. Such methods are grossly inefficient, often taking orders of magnitudes more data than humans to achieve reasonable performance. We propose Neural Episodic Control: a deep reinforcement learning agent that is able to rapidly assimilate new experiences and act upon them.
A set of of excellent introductory tutorials on statistical data mining and machine learning written by Andrew Moore (Carnegie Mellon University & Google)
A one-day tutorial/workshop for Caffe, framework for building convolutional neural networks
The wide range of organizational complexity, in combination with their relatively simple and accessible nervous systems, makes invertebrates excellent models to study general sensory coding principles – a free ebook from Frontiers.org
In the robotics community there is an increasing interest in reproducing sensorimotor mechanisms in artificial agents, mainly motivated by the aim of producing autonomous adaptive systems that can deal with complexity and uncertainty in human environments.
As time passes, memories transform from a highly detailed state to a more gist-like state, in a process called “memory transformation.” In this work, we demonstrate a view of memory transformation that defines it as a way of optimizing behavior across multiple timescales.
How does the brain learn about the regularities in the environment? the Turk-Browne lab at Princeton studies how the human brain implements statistical learning.
A fully integrated and accelerated deep learning system for businesses and organizations using artificial intelligence, machine learning and cognitive systems