Statistical models for neural data: from GLMs to latent variables (Part 1)

1. Introduction to the neural coding problem: how are stimuli and actions encoded in neural activity?
2. What aspects of neural activity carry information?
3. Regression models, latent variable models: aim to capture hidden structure underlying neural activity
4. Model fitability/tractability vs richness and flexibility, finding a "sweet spot" in between

Outline

Spike count models and maximum likelihood
  simple example #1 (21:46): linear Poisson neuron, maximum likelihood estimation, log-likelihood
  simple example #2 (42:22): linear Gaussian neuron
  example #3: (50:17): unknown neuron, basic Poisson GLM
Spike train models (GLMs with spike history)
  What is a GLM? (57:20)
  Design matrix (1.00.07)
  GLM summary (1.20.18)
Multiple spike train models (GLMs with coupling)
  GLMs with spike history and coupling (1.23.19)
  GLM dynamic behaviour examples (1.34.43)
Regularisation
Beyond GLM
Latent variable models