Discover maragraziani/concept_discovery

Stars
13
Rank 1,512,713 (Top 30 %)
Language
Jupyter Notebook
License
MIT License
Created almost 2 years ago
Updated about 1 year ago

maragraziani

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Automatic identification of regions in the latent space of a model that correspond to unique concepts, namely to concepts with a semantically distinct meaning.

interpretAI_DigiPath

Hands-on Sessions 1 and 2 at the Building Interpretable AI for Digital Pathology AMLD workshop 2021

Jupyter Notebook

interpretableWSItoRNAseq

An interpretable approach based on trainable attention that identifies which regions in H&E slides of colorectal cancer are the most informative about RNA transcriptomics

Python

ConceptAttribution

With this library you will be able to apply concept attribution to your task. You will find the functions to compute concept measures on your data, to learn the regression concept vectors and to generate concept based explanations.

Python

miccaihackathon_shifts

Jupyter Notebook

XAI_evaluation

This repository contains the code and results of the paper "Evaluation and Comparison of CNN Visual Explanations for Histopathology", to be presented at the XAI Workshop at AAAI-21.

Jupyter Notebook

InterpretabilityVISUM22

Hands-on session on Interpretable AI at the VISUM Summer School 2022

Jupyter Notebook

multitask_adversarial

Repository for our work on multi task adversarial CNNs

Jupyter Notebook

medgift-VisBreastHist

Visual interpretability for patch-based classification of breast cancer histopathology images. (in review)

intentionally_flawed_models

This repository contains the scripts to replicate the experiments in Interpreting Intentionally Flawed Models with Linear Probes

Jupyter Notebook

cam-toroidal-smooth-LSTMs

Improving Interpretability and Generalisation in Deep Learning. Thesis work for the MPhil in Machine Learning, Speech and Language Recognition at University of Cambridge, Engineering Department.

Python

cam-4M17-normApproximation

MATLAB

IMVIP2019

This reporitory contains the code for replicating the experiments in "Visualizing and interpreting feature reuse of pretrained CNNs for histopathology", submitted as a short abstract at IMVIP2019.

Jupyter Notebook

cam-kaggle-ML-major

Jupyter Notebook

maragraziani.github.io

Personal Website

CSS

cam-4M17

MATLAB

medgift-KerasAugmentation

Improved Data Augmentation for CNN training with keras.

tdd-bdd-final-project

Final project IBM introduction to TDD/BDD coursera

Python

intro-interpretableAI

Repository of the main source code for the assignments of the "Introduction to interpretable AI" course

Jupyter Notebook

maragraziani/concept_discovery_svd

maragraziani

Reviews

Repository Details

More Repositories