DSC180A-Methodology-5

| Shuyu Wang (shw043@ucsd.edu) | Section A07, Professor Mikio Aoi

What is the most interesting topic covered in your domain this quarter?

GPFA is learned as the method for extracting neural trajectories and aiding in the analysis of neuron activities by combining smoothing and dimensionality reduction. It is intriguing to understand how these methods improve predictions compared to two-stage methods.

Describe a potential investigation you would like to pursue for your Quarter 2 Project.

I am interested in learning and developing novel models applicable to neuroscience experiments. Specifically, I aim to decode spike data to uncover potential connections among neural signals and decision-making. Additionally, I intend to assess whether I can accurately predict animal decisions using the available data.

What is a potential change you’d make to the approach taken in your current Quarter 1 Project?

I may change the packages and code we use for making the models about GPFA. Since we are now just using the data generated by ourselves, we need to change our solutions when we are using true dataset.

What other techniques would you be interested in using in your project?

I am interested in incorporating the EM algorithm. Additionally, as part of the data analysis, I would like to explore the distinctions in filtering data between normal data and signal data, as well as variations in visualization techniques.