Name: Minal S Patil
Type: User
Company: Umeå universitet
Bio: Explainable AI, Counterfactual Theory and Causal Inference, Neural-Symbolic Learning, Machine Reasoning, (Lifelong) Reinforcement Learning
Location: Umeå, Sweden
Blog: https://minalspatil.github.io/
Minal S Patil 's Projects
Resources for deep learning with satellite & aerial imagery
Leveraging Ontological Schema Information in Embedding Models for Knowledge Graphs
A game theoretic approach to explain the output of any machine learning model.
Shapash makes Machine Learning models transparent and understandable by everyone
With the aim of building next generation virtual assistants that can handle multimodal inputs and perform multimodal actions, we introduce two new datasets (both in the virtual shopping domain), the annotation schema, the core technical tasks, and the baseline models. The code for the baselines and the datasets will be opensourced.
machine learning with logical rules in Python
Skyscapes - Fine-Grained Semantic Understanding of Aerial Scenes
A system for quickly generating training data with weak supervision
An educational resource to help anyone learn deep reinforcement learning.
Stanford Method for Persistent Scatterers
VIP cheatsheets for Stanford's CS 229 Machine Learning
Streamlit — The fastest way to build data apps in Python
An extensive evaluation and comparison of 28 state-of-the-art superpixel algorithms on 5 datasets.
PyTorch implementation of "Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning"
A set of jupyter notebooks for the practice of TDA with the python Gudhi library together with popular machine learning and data sciences libraries.
An open source reinforcement learning framework for training, evaluating, and deploying robust trading agents.
git tutorial
The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.
Convert matplotlib figures to TikZ/PGFplots for smooth integration into LaTeX.
LaTex Poster for TOM-Net (CVPR 2018)
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
TensorFlow Reinforcement Learning
To Trust Or Not To Trust A Classifier. A measure of uncertainty for any trained (possibly black-box) classifier which is more effective than the classifier's own implied confidence (e.g. softmax probability for a neural network).
A Tufte-inspired LaTeX class for producing handouts, papers, and books
U-Net Brain Tumor Segmentation
UCL Deciding, Acting, and Reasoning with Knowledge (DARK) Lab
Resources and student assignments for the WASP Software Engineering course