Neural Decoding of Spike Trains and Local Field Potentials with Machine Learning in Python

Explore neural decoding principles from a machine learning perspective in this comprehensive computational tutorial using Python. Delve into data preprocessing, model selection, and optimization techniques for decoding neural information from spike trains and local field potentials. Analyze a dataset containing neural information from six cortical areas of the macaque brain, spanning from the frontal to the occipital lobe. Learn about the importance of neural decoding, cross-validation methods, and the pipeline for coding analysis. Gain hands-on experience with open-source packages, machine learning basics, and various classifiers including Linear Support Vector Machines, Extra Trees, and Random Forests. Follow along using Anaconda Python 3.7, Jupiter notebooks, and provided datasets to practice loading data, plotting functions, and defining classifiers. Benefit from the expertise of Omar Costilla Reyes, a postdoctoral researcher at the Miller Lab, MIT, specializing in machine learning methodologies for understanding neural dynamics in cognitive neuroscience.

Introduction
Overview
Example spike train
Stimulus
Why neural decoding is important
Pipeline of coding analysis
Crossvalidation
Data set
Experiment
Explanation
Brain videos
Objectives
Title
Open source packages
Machine learning basics
Linear support vector machine
Extra trees
Cross validation
Tutorial
Anaconda
Jupiter
Random Forest
Notebook
Loading the data
Loading the motion data
Plot function
Changing number of trials
Defining the classifier