# MH3520 (Autumn, 2024)¶

MH3520: Mathematics of Deep Learning

Lectures: Tue 15:30 - 17:20, Thur 13:30 - 15:20

Office Hour: Thur 15:30 - 16:20

Lecture Handout: `handout`

. Contents are subject to change on a running basis. The most updated version will only be uploaded to NTULearn.

Instructor: Zhongjian Wang (zhongjian dot wang at ntu dot edu dot sg).

## Pre-requisites¶

The following courses are prerequisites:

**MH2100 Calculus III**: Differential calculus in multiple dimensions is needed for continuous optimization methods such as gradient descent.**MH3500 Statistics**: Some basic notions and results of probability theory and asymptotic statistics are needed for statistical learning theory.**MH3600 Introduction to Topology**: Point-set topology and functional analysis are needed for function approximation theory.**PS0001 Introduction to Computational Thinking**: You should be able to derive simple algorithms and code them in Python.

Please let me know if you feel that your background in any of these areas is insufficient. There will be opportunities for getting everyone on track.

The above requirement is **strictly non-waivavle** in ensure the expected outcome of learning.

## Course Policies¶

### Homework (20%)¶

Weekly assigned, may involves mathematical derivation and coding in Python.

### Presentation (20%)¶

You are require to present your solution to the homework or related material during the tutorial of each week.

### Exams (60%)¶

There will be a final exam counts 60% which requires you to do some short answer questions. Calculator may be allowed but will not be useful.