RNN for biological neural networks
Project Description

Artificial Recurrent Neural Networks (RNN) such as LSTM and GRU have recently gained intense interest in machine learning. These models are highly versatile and achieve breakthrough performance in many applications of sequential data.

In this project, we will (1) use RNN to model the complex temporal dynamics of real neural networks in the brain (2) and explore variations of RNN that are biological plausible with interpretable parameters that can be potentially linked to anatomical structures and biophysical properties.

Supervisor
HU Yu
Quota
1
Course type
UROP1100
UROP2100
UROP3100
UROP4100
Applicant's Roles

1. Fit RNNs to large scale neural activity data and interpret the biological insights of the results
2. Evaluate the performance of different simplified RNNs on machine learning benchmark datasets

The student is expected to commit at least 8 hours per week on the project.

Applicant's Learning Objectives

The student will (1) grasp the basics of how use RNN for time series/sequence data, and (2) learn about the structure and dynamical properties of biological neural networks.

Complexity of the project
Challenging