I teach the modules Adaptive Intelligence and Modelling and Simulation of Natural Systems to 3rd year undergraduate and MSc students. Clicking on their names will take you to their corresponding web pages.


COM3240 Adaptive Intelligence

Prerequisites

In addition to excellent programming skills, Matrix Algebra and very good knowledge of Calculus (derivatives) is required for this course. Python or Matlab will be used for the laboratory exercises.

Evaluation 

Assignments (35%) and a formal exam (65%).

Bibliography

The reading material for this course includes a selection from the books: "Introduction to the Theory of Neural Computation" by Hertz, Krogh & Palmer, "Spiking Neuron Models" by Gerstner & Kistler, "Theoretical Neuroscience" by Dayan & Abbot and "Reinforcement Learning: An Introduction" by Sutton & Barto.


COM3001/6009 Modelling and Simulation of Natural Systems

Prerequisites

The course requires that students have very good programming skills (and some experience with Matlab) and at least A-level mathematics background. It also requires self-study of the provided material and any additional revision material one may need, e.g. calculus, in order to get an in depth understanding of these techniques. 

Evaluation

10 credit version (COM3001): Assignment (40%) and a formal exam (60%). 15 credit version (COM6009): Assignments (65%) and a formal exam (35%).

Bibliography

For the Mathematical Modelling part of the course: (i) A selection from Chapters 1 and 11, "Differential Equations, Dynamical Systems & An Introduction to Chaos", by Hirsch, Smale and Devaney. (ii) Chapter 20 from "Applied Numerical Methods with Matlab for Engineers and Scientists" by Chapra. (iii) Chapter 1 and sections 4.1, 4.2 from "Spiking Neuron Models" by Gerstner & Kistler.

© Eleni Vasilaki 2017