SOURCE-LINKED INTELLIGENCE

Statistical Mechanics of Deep Residual Networks in the Feature Learning Regime

CORDIS · observation · Publication date unknown

residual nets in the feature learning regime, providing low-dimensional predictive models that theoretically describe their behavior through scaling limits; (ii) addressing two major open problems in deep learning theory: the computation of the Neural Scaling Law exponents and the implementation of hyperparameter transferability, by analytically exploiting the predictive capabilities of the aforementioned foundational theories. SM-DeepResNet synergizes the applicant’s core competency in computational physics with the supervisors' expertise in statistical mechanics (host institution) and in deep learning mathematics (associated partner). The main purpose of this broad program is to unveil the entangled roles of structured data, width and depth in overparameterized deep residual neural networks, ultimately contributing to the development of effective strategies for the next generation of AI architectures." Machine Learning, Neural Networks, Deep Learning Theory, Statistical Mechanics

Read original source ↗ Open in workspace

recordType

award

status

SIGNED

region

EU

value

396991.08

unit

EUR