We analyze the knowledge acquired by AlphaZero, a neural network engine that learns
chess solely by playing against itself yet becomes capable of outperforming human chess …

It is unclear how changing the learning rule of a deep neural network alters its learning
dynamics and representations. To gain insight into the relationship between learned …

Interactions across frontal cortex are critical for cognition. Animal studies suggest a role for
mediodorsal thalamus (MD) in these interactions, but the computations performed and direct …

Abstract Recently proposed Gated Linear Networks (GLNs) present a tractable nonlinear
network architecture, and exhibit interesting capabilities such as learning with local error …

The dominant view in neuroscience is that changes in synaptic weights underlie learning. It
is unclear, however, how the brain is able to determine which synapses should change, and …

The state-of-the art machine learning approach to training deep neural networks,
backpropagation, is implausible for real neural networks: neurons need to know their …

Backpropagation (BP) uses detailed, unit-specific feedback to train deep neural networks
(DNNs) with remarkable success. That biological neural circuits appear to perform credit …

Aiming to solve the challenges of difficult training, mode collapse in current generative
adversarial networks (GANs), and the efficiency issue of requiring multiple samples for …

Machine learning has witnessed substantial growth, leading to the development of
advanced artificial intelligence models crafted to address a wide range of real-world …

A key challenge for AI is to build embodied systems that operate in dynamically changing
environments. Such systems must adapt to changing task contexts and learn continuously …