The primary objective of this project was to decode and understand the motor responses of rats in reaction to tilting events, leveraging machine learning tools to analyze neural spike times from the motor cortex. Initially, the task involved organizing the recorded spike time data, followed by creating perievent rasters and histograms to visually represent the neural activity. The key tool developed was a Peri-Stimulus Time Histogram (PSTH) classifier, aimed at categorizing the different motor responses to clockwise and counterclockwise tilts. To further refine the classification performance, Principal Component Analysis (PCA) was integrated with the PSTH classifier. The methodologies employed were inspired by the paper by Foffani and Moxon (2004).

--> Week 1: Creating raster plots, peri-stimulus time histograms (PSTH), and receptive field analysis.

--> Week 2: Calculating the entropy of a spike train, the mutual information between two neurons, and the joint mutual information for multiple stimuli.

--> Week 3: Developing a PSTH classifier.

--> Week 4: Principal component analysis (PCA) + PSTH classifier.

Foffani, G., & Moxon, K. A. (2004). PSTH-based classification of sensory stimuli using ensembles of single neurons. Journal of neuroscience methods, 135(1-2), 107–120. https://doi.org/10.1016/j.jneumeth.2003.12.011