About

This is a freely available online course on neuroscience for people with a machine learning background. The aim is to bring together these two fields that have a shared goal in understanding intelligent processes. Rather than pushing for “neuroscience-inspired” ideas in machine learning, the idea is to broaden the conceptions of both fields to incorporate elements of the other in the hope that this will lead to new, creative thinking. Note that if this page is causing you scrolling issues on iPhone Safari, click here.

The course is given in person at the Department for Electrical and Electronic Engineering, Imperial College London, and made freely available online (although without the practical classes).

Each week there are a series of videos to watch on YouTube, and a set of exercises available as a Jupyter notebook that can be run locally or via Google Colab. Students at Imperial College can discuss on Teams, and for everyone else there is an open Discord server.

We hope you enjoy the course!

Quick links

Week by week

Week 0 - Introduction and motivation

Why neuroscience? (slides)
Course outline (slides)
History of neuroscience and machine learning (slides)
Challenges for machine learning and neuroscience (slides)
No exercises this week
Reading material

Week 1 - Neurons

Neuron structure (slides)
Neuron function (slides)
Abstract neuron models (slides)
Biophysical neuron models (slides)
Code for figures: Preview notebook /
Exercises: Intro video / Preview notebook /
Reading material

Week 2 - Synapses and networks

Synapses 1 (slides)
Synapses 2 (slides)
Networks (slides)
Synapse models (slides)
Network models (slides)
Code for figures: Preview notebook /
Exercises: Intro video / Preview notebook /
Reading material

Week 3 - Brain structure

Connectome (slides)
Humans (slides)
Exercises: Intro video / Preview notebook /
Reading material

Week 4 - Learning rules

Types of learning (slides)
Rate-based models (slides)
STDP (slides)
Code for figures: Preview notebook /
Exercises (outline only): Preview notebook /
Reading material

Week 5 - Spiking neural networks

Spiking is not differentiable (slides)
Training SNNs with limited gradients (slides)
Training SNNs with surrogate gradients (slides)
Training SNNs with approximate gradients (not finished yet, coming soon)
Exercises: Intro video not yet recorded / Preview notebook /
Reading material

Week 6 - Understanding neural networks

Observing (slides)
Analysing (slides)
Manipulating (slides)
Exercises: Intro video / Preview notebook /
Reading material

Week 7 - Various topics

Only one video this week, more will be added in future.

Decision making (slides)
Code for figures: Preview notebook /
No exercises this week
Reading material

Week 8 - Neuromorphic computing

This week’s videos feature research by Gabriel Béna (although any errors you find are probably the result of Dan’s interference).

Week 9 - Open issues

Does neuroscience work? (slides)
What are spikes for? (slides)
Code for figures: Preview notebook /
Exercise this week is to resolve some of the open issues discussed. Good luck!
Reading material

Accessibility

The Powerpoint slides contain (in the speaker notes) a complete transcript of everything we say.

Youtube automatic captions are of reasonable quality, and after the course is complete we will update them with manual transcripts. For the moment, the Powerpoint slides and automatic captions can be used.

Extended reading list

There is no required reading for this course, only optional. We will be curating a list of papers that are meant to be about inspiring creativity and joy in this field. For the moment though, you can check out:

Credits

Dan Goodman: course design
Marcus Ghosh: course design
Gabriel Béna: research for week 8, neuromorphic computing
Swathi Anil: beta testing, feedback, teaching assistant
Greta Horvathova: beta testing, feedback, teaching assistant

Citing us

Please cite us via our Zenodo record:

Goodman, Dan F. M., and Marcus Ghosh. ‘Neuroscience for Machine Learners’. 12 December 2023. https://doi.org/10.5281/zenodo.10366802.