COMP 551: Applied Machine Learning — Project #4
-
Updated
Apr 18, 2017 - Jupyter Notebook
COMP 551: Applied Machine Learning — Project #4
Towards Understanding Deep Learning Representations via Interactive Experimentation
Results of binary classification of Yelp reviews as pertaining to conventional or alternative medicine using random forests
A collection of infrastructure and tools for research in neural network interpretability.
This repository contains code, information and datasets for the project on making interpretable models titled "Model Agnostic Methods for Interpretable Machine Learning". The abstract can be accessed at https://docs.google.com/document/d/1k2-beHD4YQxXpH8ExUM2Gd-yE5VqdluhiCsUIO3czRM/edit?usp=sharing
Proposed Solution for the Predictive Modelling Cajamar Challenge 2018
Using LIME (Local Interpretable Model-Agnostic Explanations) for text data
IILasso: Independently Interpretable Lasso
On the importance of single directions for generalization(Morcos et al, ICLR 2018)
[ECCV 2018] code for Choose Your Neuron: Incorporating Domain Knowledge Through Neuron Importance
A web user interface for the OncoText Pathology System (https://github.com/yala/OncoText)
IEEE TVCG Visual Analytics in Deep Learning Survey
Optimizing Mind static website v1
OncoText is an information extraction service for breast pathology reports. It supports over 20 categories including DCIS, includes pretrained models, and supports flexible addition of new categories, new training data, and parsing new reports.
Paper for 2018 Joint Statistical Meetings: https://ww2.amstat.org/meetings/jsm/2018/onlineprogram/AbstractDetails.cfm?abstractid=329539
Implementation of "Toward an Interpretable Alzheimer's Disease Diagnostic Model with Regional Abnormality Representation via Deep Learning"
Trefle is a scikit-learn compatible estimator implementing the FuzzyCoCo algorithm that uses a cooperative coevolution algorithm to find and build interpretable fuzzy systems.
Add a description, image, and links to the interpretability topic page so that developers can more easily learn about it.
To associate your repository with the interpretability topic, visit your repo's landing page and select "manage topics."