Course Name: NeuroData Design
Neurosim
Extracellular electrophysiological simulations, and comparative analysis of various spike sorting algorithms with ground truth validation.
Neural Anatomy and Optical Microscopy (NAOMi) Simulation Translation for Increased Efficiency and Accessibility to Ground-truth Calcium Imaging Data
The Neural Anatomy and Optical Microscopy (NAOMi) is a first-in-class approach in that it is the only existing framework for...
Deep Learning Methods for Automated Gleason Grading
Prostate cancer remains the second most common cause of death among men worldwide. It is challenging to treat, with early...
M-PHATE for RNNs
Developing a visualisation method to observe the internal dynamics of recurrent neural networks.
Surgical Activity Recognition Using TD-CNN-LSTM Model
Activity recognition is one of the most essential and challenging tasks in computer vision. The development of a precise activity...
Generative Approaches to Shapley-based Explanations
Our group leverages advances in generative learning to develop more statistically accurate, computationally feasible post-hoc Shapley-based explanations for medical computer...
Brainlit
Understanding the structure of the brain can lead to advances in treating neurological disorders. Our team is developing Brainlit, a...
Graph Statistics in the Brain
Inherent variability within a single network or populations of networks is an increasingly desirable phenomenon to characterize. Implications of this...
M2G
Connectomes are brain mappings that allow us to understand the variability in brain connectivity and brain function. Currently, there is...
Mouse
The connectome is a comprehensive map of the structural and functional connections of the brain, derived from multiple neuroimaging modalities....
mvlearn
In many datasets, there are multiple measurement modalities of the same subject, i.e. multiple X matrices (views) for the same...
Tealeaf
Random Forest (RF) is an interpretable and robust machine learning algorithm for classification and regression. However, existing RF methods are...
Improving Adversarial Task Transfer in Lifelong Learning Models via Domain Adaptation
Lifelong learning is a paradigm proposed to address catastrophic forgetting as new tasks are introduced and learned by a model....
RF/DN: Analysis of Random Forests and Deep Networks with Varying Sample Sizes
Random forests (RF) and deep networks (DN) are two of the primary machine learning methods in current literature, yet they...