deeplift

Public facing deeplift repo

Pytorch implementation of various neural network interpretability methods

Enhanced CNN model for malaria cell classification, featuring Class Activation Mapping (CAM) as a non-agnstic technique for anomaly localization and LIME (Local Interpretable-agnostic Explanation) for interpretability, ensuring high accuracy and transparent AI diagnostics.

Code for paper 'Obtaining leaner DNN for decoding brain functional connectome in a single shot'

Source code for "Whatcha lookin'at? DeepLIFTing BERT's Attention in Question Answering."

eBM: Enhanced BRAIN-MAGNET convolutional neural network modeling non-coding regulatory elements enhancer activity in human neural stem cells

Interpretability analysis of ppiGPT protein-protein interaction predictions in Prochlorococcus MED4