Teaching

Cognitive models and artificial intelligence

Since 2020, I have taught a class on cognitive modelling and computational neuroscience with a heavy emphasis on neuroAI. This is a single-semester introductory course for the broadly multidisciplinary student cohort of the Cognitive Science master's program at ENS-PSL. As such, there are no mathematical prerequisites, although a mathematical background is helpful to get more out of the class. We cover the conceptual frameworks, assumptions, and applications of common computational models in cognitive science and neuroscience.  

Prerequisites: None 

Topics: Connectionism vs GOFAI, Hodgkin-Huxley model, neural population coding, neural manifolds, deep neural networks, Hopfield networks, continuous attractors, signal detection theory, drift diffusion model, Bayesian brain hypothesis, reinforcement learning.

(see previous syllabus for more details)

Mathematical tools for data science, machine learning, and statistical modeling

For fall 2024 I will be developing a new course on the basics of statistics and machine learning. This course is designed for students coming from quantitative backgrounds (math, physics, info) to cover the the fundamental mathematical background they will need to implement advanced statistical tools for data analysis.

Prerequisites: A solid foundation in calculus, differential equations, linear algebra, and probability theory, as well as proficiency in Python.

Topics: Sampling and resampling, information theory,  bias-variance trade-off, linear regression, optimization, regularization, gradient descent, singular value decomposition, dimensionality reduction.