Goldt Lab

Research focus

ERC Starting Grant · 2024

Beyond two-point correlations: from higher-order data statistics to neural representations

Deep neural networks (DNNs) have revolutionised how we learn from data. Rather than requiring careful engineering and domain knowledge to extract features from raw data, DNNs learn the relevant features for a task automatically from data. In particular, high-order correlations (HOCs) of the data are crucial for both the performance of DNNs and the type of features they learn. However, existing theoretical frameworks cannot capture the impact of HOCs – they either study “lazy” regimes where DNNs do not learn data-specific features, or they rely on the unrealistic assumption of Gaussian inputs devoid of non-trivial HOCs. beyond2 will develop a theory for how and what neural networks learn…

From the public funding record at EU CORDIS. Describes the funded project, not the reviews below.