Syllabus#
The primary objective of this course is to familiarize neuroscience students with the techniques and practical uses of Machine Learning (ML) within the field.
We will illustrate all practical aspects of the course through hands-on examples and applications, all of which will be showcased using the Python programming language.
Prerequisites:
Basic knowledge of programming.
Extended Mathematics course (in the Life Sciences faculty), or a parallel one.
Python Workshop:
All your assignments need to be done in Python.
If Python isn’t your strong suit, don’t worry, we’ve got you covered in the first few weeks.
Check out our self-assessment exam on the course website to see where you stand with Python. We’ve also got Python workshop videos (Video 1 and Video 2) that pretty much cover what you’d find in the first 5 chapters of the “Python for Neuroscientists” course.
We kindly request that students who aren’t familiar with Python complete the workshop to get up to speed.
Final Grade Components:
10% - Homework Assignments (80% completion required, submitted in pairs)
90% - Final Project (Quality and completion assessment)
Main topics of the course will include:
Introduction to Machine Learning, KNN.
Statistical background.
Linear regression.
Logistic regression.
Measures of goodness, bias-variance tradeoff, SVM.
Regularizations and variable selection.
Decision Trees, Bagging and Random Forest.
Boosting, Gradient Boosting, Model interpretability.
Gaussian Mixture Model, Imbalanced data, Data Leakage.
K-means, PCA, Hierarchical Clustering.
Introduction to Deep Learning.
Deep Learning in Machine Vision.
Deep Learning in Natural Language Processing.