New Special Issue on Mathematical Understanding of Information Storage, Compression and Prediction in Neural Networks

A new special issue has been announced, focusing on the mathematical analysis of deep neural networks. The issue, titled "Mathematical Understanding of Information Storage, Compression and Prediction in Neural Networks", will be hosted by either Frontiers in Computational Neuroscience or Frontiers in Neuroinformatics. The goal of the special issue is to investigate the mathematical frameworks that enable a better understanding of how information is learned and represented within a neural network, including the study of existing approaches that go in this direction.

The special issue invites researchers to present manuscripts focusing on the mathematical analysis of deep neural networks, including their information-theoretic interpretation and their statistical limits. Relevant areas include theory of deep feed-forward and recurrent NNs, information-theoretic principles and interpretation of NNs, the Information Bottleneck and deep learning, compression in deep neural networks, and many more. The manuscript submission deadline is 27 October 2024.

The topic editors for this special issue are Giorgio Gosti from the Italian National Research Council (CNR), Nicola Catenacci Volpi from the University of Hertfordshire, and Nilesh Goel from Birla Institute of Technology and Science.