Much of recent machine learning has focused on deep learning, in which neural network
weights are trained through variants of stochastic gradient descent. An alternative approach …

Evolutionary robotics applies the selection, variation, and heredity principles of natural
evolution to the design of robots with embodied intelligence. It can be considered as a …

Many fields use search algorithms, which automatically explore a search space to find high-
performing solutions: chemists search through the space of molecules to discover new …

We introduce Brain-Inspired Modular Training (BIMT), a method for making neural networks
more modular and interpretable. Inspired by brains, BIMT embeds neurons in a geometric …

Perhaps the most ambitious scientific quest in human history is the creation of general
artificial intelligence, which roughly means AI that is as smart or smarter than humans. The …

NeuroEvolution (NE) refers to a family of methods for optimizing Artificial Neural Networks
(ANNs) using Evolutionary Computation (EC) algorithms. NeuroEvolution of Augmenting …

Artificial neural networks (ANNs) have achieved significant success in tackling classical and
modern machine learning problems. As learning problems grow in scale and complexity …

Hierarchical organization—the recursive composition of sub-modules—is ubiquitous in
biological networks, including neural, metabolic, ecological, and genetic regulatory …

A long-term goal of AI is to produce agents that can learn a diversity of skills throughout their
lifetimes and continuously improve those skills via experience. A longstanding obstacle …

Modularity is a general principle present in many fields. It offers attractive advantages,
including, among others, ease of conceptualization, interpretability, scalability, module …