Neurorobotics: Sensory Representations and Learning Principles

Explores deep neural network training, optimization, preventing overfitting, and different network architectures.

Delves into the continual learning of representational models after deployment, highlighting the limitations of current artificial neural networks.

Explores rate-based Hebbian learning, covariance rules, and weight vector growth in neural networks.

Explores the inductive bias of different nonlinear supervised learning methods and the challenges of hyper-parameter tuning.

Discusses challenges in building physical neural networks, focusing on depth, connections, and trainability.