BIBFRAME Work

Title

Deep Neural Networks in a Mathematical Framework

Type

  • Monograph
  • Text

Contribution

Subject

Language

Classification

Content

Summary

This SpringerBrief describes how to build a rigorous end-to-end mathematical framework for deep neural networks. The authors provide tools to represent and describe neural networks, casting previous results in the field in a more natural light. In particular, the authors derive gradient descent algorithms in a unified way for several neural network structures, including multilayer perceptrons, convolutional neural networks, deep autoencoders and recurrent neural networks. Furthermore, the authors developed framework is both more concise and mathematically intuitive than previous representations of neural networks. This SpringerBrief is one step towards unlocking the black box of Deep Learning. The authors believe that this framework will help catalyze further discoveries regarding the mathematical properties of neural networks.This SpringerBrief is accessible not only to researchers, professionals and students working and studying in the field of deep learning, but also to those outside of the neutral network community.

Authorized Access Point

Caterini, Anthony L. Deep Neural Networks in a Mathematical Framework

Admin Metadata

  • Date: 2026-09-11T20:24:56.433143+00:00
  • Agent: cbc
  • Status: c
  • Derived from: 21770954

Admin Metadata

  • Date: 2026-09-11
  • Cataloger id: Unknown
  • Description level: http://id.loc.gov/ontologies/bibframe-2-6-0/
  • Description language: eng
  • Description authentication: pcc

Alternative Formats

Blue Core Actions

  • Load to Marva Marva loads Instances, not Works. Open one of this Work's Instances and load that into Marva instead.
  • Load to Sinopia
  • Export to Catalog Only Instances can be exported. Open one of this Work's Instances and export that instead.