Machine Learning and Neural Networks for Neuroscience

Course No: 27-504-01/02

Lecturer Name: Dr. Zvi Roth

Course Type:

Lecture

Scope of credits:

2 credit points + 1 credit point training

Year of study:

Graduate students

Semester:

A

Day & Time:

TBA

Reception Time:

___

Lecturer Email:

zviroth@gmail.com

Moodle Site:

TBA

 

 Course description and learning goals

 

Course Abstract

Machine learning (ML) is a branch of artificial intelligence that enables computers to learn a model given a large amount of data in a way that resembles human learning. Neural networks (NNs) are a type of machine learning model inspired by the structure and function of the neural networks inside the human brain.  In recent years, ML and in particular NNs have become very popular in many domains, and have been proved extremely effective in a range of applications, from machine vision and speech recognition to decision making and robotics.

 

Learning objectives

After completing the course students should understand the mathematical basis of Machine Learning, and be able to apply relevant Machine Learning techniques to real-world problems.

 

Knowledge

  1. Learners will be familiar with core Machine Learning methods.
  2. Learners will be able analyze the mathematical basis of different Machine Learning models.
  3. Learners will be aware of the pros and cons of various Machine Learning techniques.

 

Skills

  1. Learners will be able to choose appropriate Machine Learning techniques to analyze data.
  2.  Learners will be able to implement basic Machine Learning models in real-world situations.

 

Active learning – lessons plan

You can plan an active learning process for the entire course or listfor each active learning activity lesson in the following table:

 

Lesson No.

Topic

Active learning

Required reading

Assessment

1

Introduction

 

 

 

2

Linear regression

 

 

 

3

Classification, Regularization

 

 

 

4

Generalized linear models

 

 

 

5

Generative algorithms, Model evaluation

 

 

 

6

Decision Trees

 

 

 

7

Support vector machines

 

 

 

8

Kernels

 

 

 

9

Artificial neural networks: Perceptron, MLP, Backpropagation

 

 

 

10

Unsupervised learning

 

 

 

11

Autoencoders

 

 

 

12

Generative adversarial networks

 

 

 

13

Natural language processing

 

 

 

14

Review

 

 

 

(In a course that lasts a whole year, the additional sessions should be added)

* There may be changes in the syllabus depending on learning progress and effectiveness

 

Final grade   

Description of the learning product

Weight in the final score

Final project

Will account for 45% of the final grade

Home assignments

30% of final grade

Midterm exam

25% of final grade

 

Course requirements

Students must submit 80% of home assignments, and the final project.

 

 Prerequisites

  • Mathematics: Probability and statistics, Linear Algebra, Calculus.
  • Fluency in a programming language preferably Python.

 

Bibliography: Up-to-date reading, viewing, and listening content items

 

  • Machine Learning and Pattern recognition, C. Bishop (2006)
  • Deep Learning, I. Goodfellow and Y. Bengio (2015)
  • The Elements of Statistical Learning, T. Hastie et al. (2001)