Machine Learning for Neuroscience
CAJAL Advanced Neuroscience Training (2023)
website
We provide teaching about AI-driven brain-wide credit assignment as part of this new Cajal course.
MSc in Neuroscience
University of Oxford (2023-)
website
We will be contributing to the interdisciplinary and interdepartmental MSc in Neuroscience.
NeuroAI workshop
Max Planck Institute for Brain Research (2023)
website
We provided teaching/tutorials for the Bio-inspired deep learning workshop organised by Max Eggl and Laura Timón at the Max Planck Institute for Brain Research in Frankfurt.
Information Processing & the Brain [COMSM0075]
University of Bristol (2018-2023)
Github repo
The brain is the most remarkable learning and information processing system that we know of. In this unit we teach information and statistical theories of the brain, different learning paradigms in neuroscience (unsupervised learning, supervised learning, reinforcement learning and deep learning) and advanced data analysis methods. Taught together with Conor Houghton and Cian O’Donnell.
Machine Learning [COMS30035]
University of Bristol (2020-2023)
Github repo
This unit seeks to acquaint students with machine learning algorithms which are important in many modern data and computer science applications. We cover topics such as kernel machines, probabilistic inference, neural networks, PCA/ICA, HMMs and emsemble models. Taught together with James Cussens and Edwin Simpson.
Mathematics for Computer Science A [COMS10014]
University of Bristol (2020-2023)
Github repo
This unit and its companion Mathematics B teach you the basic mathematics that you will need in your Computer Science degree. The topics have been selected based on the needs of units in later years linked to some of our research areas, for example algorithms, machine learning, data science or computational neuroscience as well as topics in statistics that will be of interest to many students when they perform experiments or evaluations in their final project. Taught together with Conor Houghton, Kerstin Eder and David Bernhard.
Symbols, Patterns and Signals [aka Data science for CS; COMS21202]
University of Bristol (2019-2020)
Github repo
This unit seeks to acquaint students with the fundamental aspects of processing digital data, presented in the context of concrete examples from applications in computer vision, graphics, speech, audio, machine learning and data mining. Particular emphasis is placed on the importance of representation and modelling. Taught together with Laurence Aitchison and Majid Mirmehdi.
Computational Neuroscience [COMS30127]
University of Bristol (2018-2019)
Github repo
There is a growing need to describe with computational models the growing datasets that neuroscience is producing. This unit teaches the fundamentals of computational modelling in neuroscience (e.g. neuron and synaptic models). Contribute together with Conor Houghton, Cian O’Donnell and Laurence Aitchison.
Others
- Tutorial on modelling synaptic plasticity:
This tutorial was design to give a 1h taster session of computational modelling of synaptic plasticity for the international PhD module on Synapses, neuronal circuits and behavior (supported by FENS/IBRO-PERC) at University of Coimbra, Portugal. You can try the tutorial here.
Made with Jekyll based on Kording Lab template.