Final Project
The goal of the final project is to demonstrate mastery over one of the topics of the course by replicating a key result from a published paper from the last decade or two. Before beginning serious work on your project, you should send a “project abstract” email with an outline of what paper and what figure(s) you plan to replicate. (In some cases it may be suggested to reduce the scope or simplify the plan!) Please do this by the end of the Thanksgiving break to ensure you have enough time to work.
Below are some suggested / sample papers that you might consider. This is not intended to be an exhaustive list, and students have in the past even proposed using one of the techniques from the class on a topic of their own interest (e.g., clustering of fantasy football players).
Point Processes
Classification
- Kemere et al 2004 “Model-based decoding of reaching movements for prosthetic systems.”
- Yu et al 2004 “Improving neural prosthetic system performance by combining plan and peri-movement activity.”
- Santhanam et al 2009 “Factor-analysis methods for higher-performance neural prostheses.”
Clustering
- Wild et al 2012 “Performance comparison of extracellular spike sorting algorithms for single-channel recordings.”
- Calabrese and Paninski 2011 “Kalman filter mixture model for spike sorting of non-stationary data.”
- Zhang, Lee, Rozell and Singer “Sub-second dynamics of theta-gamma coupling in hippocampal CA1.”
Dimensionality Reduction
- Yu et al 2009 “Gaussian-process factor analysis for low-dimensional single-trial analysis of neural population activity.”
- Churland et al 2012 “Neural population dynamics during reaching” (specifically jPCA, e.g., Figure 3)
- More ideas here: Cunningham and Yu “Dimensionality reduction for large-scale neural recordings”
- [Wu et al 2017 “Gaussian process based nonlinear latent structurediscovery in multivariate spike train data.”‘(https://pillowlab.princeton.edu/pubs/Wu17_PoissGPLVM_nips.pdf)
- Pandarinath et al 2018 “Inferring single-trial neural population dynamics using sequential auto-encoders.”
Continuous decoding
- Kemere and Meng 2005 “Optimal estimation of feed-foward-controlled linear systems”
- Wu et al 2004 “Modeling and decoding motor cortical activity using a switching Kalman filter.”
- Brown et al 1998 “A statistical paradigm for neural spike train decoding applied to position prediction from ensemble firing patterns of rat hippocampal place cells.”
- Quang et al 2015 “The Kalman Laplace filter: A new deterministic algorithm for nonlinear Bayesian filtering”