Induction week classes
|25/09/172 - 4pm
||Intro to neuroanatomy and sensory pathways.
||Kirsty McNaughtJesse Geerts
Sensory pathway slides
|26/09/172 - 3.30pm
||Intro to vector spaces (prerequisites for kernels course)
||Michael ArbelWenkai Xu
Kernels background notes
|27/09/1711am - 12.30pm
||Basics of linear algebra
||Jorge Menendez Canelas
Linear algebra notes
|27/09/172 - 4pm
||Using source control and intro to git
||Kirsty McNaughtSteve LenziCharly Rousseau
Version control slides
|28/09/1710.30am - 12.30pm
||Intro to applied Bayesian methods (prerequisites for machine learning course)
Stats background notes
|28/09/172 - 4 pm
||Basic cell biology and experimental methods
||Matt PhillipsSteve Lenzi
|29/09/173 - 4.30pm
||Practical PhD skills and tips, Q&A with students
PhD skills notes
Below are some notes made by previous students. They may contain errors; you are strongly encouraged to report back to us and contribute changes. There is significant overlap in some areas; pick the perspective you prefer.
|Full TN Notes
||Jorge's TN notes
||A somewhat comprehensive set of notes covering the main parts of the course. Should be particularly useful for mean-field theory of networks. Also includes a list of useful papers to read.
||Jorge's correlations notes
||Some handwritten notes on Peter Latham's lecture on differential correlations (Moreno-Bote et al, 2014)
||Learning rules (Kirsty)
||Mainly plasticity/hebbian rules, summarised from Dayan&Abbott.
||Covers most of Peter Latham's biophysics, at a higher level than Jorge's more comprehensive notes
|Information theory for TN
||Information Theory (TN) (Kirsty)
||High level definitions and relationships between Information Theory terms
Machine Learning (including kernels)
It is highly recommended that you use latex for your assignment in this course and others. You may find it helpful to start with this sample assignment template, which demonstrates some figures, maths and other useful things.