Humans and animals excel at generalizing from limited data, a capability yet to be fully
replicated in artificial intelligence. This perspective investigates generalization in biological …

Despite the practical success of deep neural networks, a comprehensive theoretical
framework that can predict practically relevant scores, such as the test accuracy, from …

Empirical data, on which deep learning relies, has substantial internal structure, yet
prevailing theories often disregard this aspect. Recent research has led to the definition of …

To achieve near-zero training error in a classification problem, the layers of a feed-forward
network have to disentangle the manifolds of data points with different labels to facilitate the …

Statistical physics provides tools for analyzing high-dimensional problems in machine
learning and theoretical neuroscience. These calculations, particularly those using the …

Understanding how neural systems efficiently process information through distributed
representations is a fundamental challenge at the interface of neuroscience and machine …

The study of the brain encompasses multiple scales, including temporal, spatial, and
functional aspects. To integrate understanding across these different levels and modalities, it …

A key problem in deep learning and computational neuroscience is relating the geometrical
properties of neural representations to task performance. Here, we consider this problem for …

Higher brain functions depend on experience-dependent representations of relevant
information that may be organized by attractor dynamics or by geometrical modifications of …

Dogs display vast phenotypic diversity, including differences in height, skull shape, tail, etc.
Yet, humans are almost always able to quickly recognize a dog, despite no single feature or …