Pre-start

Announcements

  • Office hours today 4-6ish BRC Cafe
  • HW 3 "due" today
  • HW 4 to be released this weekend 
    • Try not to fall behind. Just complete everything and it's  probably an A or you can correct HWs based on feedback...see below!
  • Self-grading note: I'd ideally like everyone to submit a self grade of each problem given the objectives that are listed. Primarily, I want to know how confident you are in what you have submitted. We will provide you feedback no matter what you assign and assign you points that we think BUT these are just opinions. Self-valuation is the only thing that means anything. Outside of that you can correct whatever for points back.

Neural Signal Processing & Machine Learning

ELEC/BIOE 548 | ELEC 483

Fall 2022

Episode 17: Spike sorting intro finale and Clustering with math and stuff!

1

Introduction. Class & brains

2

Fundamental neurobiology. How do neurons fire? How/what do we record?

3

Modeling spike trains. First bit of analysis work and understanding firing properties of neurons.

5

Classification. Making machines learn. Which direction is a monkey trying to reach? Bayesian decoding.

4

Point processes. Continued modeling work of neurons.

6

Clustering/Mixture models. Making machines learn some more. Spike sorting.

Bi-weekly Schedule

7

Continuous decoding. Kalman filters. Machines continue to learn.

8

Spectral analysis? LFP interpretation in spectral domain. But also kinda in clustering.

Brain Signals!

  • How can we measure neural activity?

  • What info do neurons encode in trains of action potentials (“spike trains”)?

  • How can we model “statically” encoded information?

  • Estimation/”decoding”

  • Signal conditioning – “spike sorting” (PCA, Expectation-Maximization)

  • How can we model/decode “dynamic” information? (filtering, Kalman, HMM)

  • Beyond spike trains (LFP, EEG, imaging)

LFP Clustering

LFP Clustering

LFP Clustering

LFP Clustering

Clustering Math!

Expectation-Maximization

Iteration Number

After E-step 1

After M-step 1

Cost function decreases during K-Means

back to spike sorting

ELEC548 Lec18

By Shayok Dutta

ELEC548 Lec18

  • 60