Mathematical Structures of Deep Neural Networks

Utbildningsfakta

Kod: MMA440

The goal of this course is to give an overview of the mathematical structures that appear in modern deep neural networks and enable students to understand current research literature in the field. To this end, the course starts with a concise introduction to the field of deep learning followed by deeper dives into the topics of equivariant neural networks, large width neural networks and geometrical aspects of explainable AI. The lectures are accompanied by computer labs where students learn the basics of implementing neural networks.

Behörighet

General entry requirements and the equivalent of the courses MSG110 Probability Theory, MVG301 Programming with Python, and MMG500 Algebraic Structures. In addition to these requirements, it is also desirable with knowledge corresponding to the courses DIT013 Imperative Programming with Basic Object Orientation, MMA211 Higher Differential Calculus, and MMA201 Representation Theory.

Utbildningstillfällen

Varje tillfälle har egna datum och villkor. Avslutade tillfällen behålls som historik och innebär inte att en ny ansökan är öppen.

• Mathematical Structures of Deep Neural Networks

  University of Gothenburg

  Startdatum: 19 januari 2026

  Slutdatum: 22 mars 2026

  Studietakt: 50 %