akshathmangudi/tnn
Tversky Neural Networks.
This project provides an alternative way for AI practitioners and researchers to build image classification models. Instead of traditional neural network layers, it uses Tversky similarity to compare images to learned 'prototypes,' making the decision-making process more understandable. You can input image datasets like MNIST and get out highly accurate classification models that are easier to interpret.
No commits in the last 6 months.
Use this if you need to build image classification models where understanding *why* a model makes a certain decision is as important as its accuracy.
Not ideal if you primarily work with non-image data or require the absolute bleeding edge in model accuracy without concern for interpretability.
Stars
8
Forks
2
Language
Python
License
MIT
Category
Last pushed
Aug 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/akshathmangudi/tnn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
tflearn/tflearn
Deep learning library featuring a higher-level API for TensorFlow.
DingKe/nn_playground
Experimental keras implementation of novel neural network structures
DataForScience/DeepLearning
Deep Learning From Scratch
OVVO-Financial/NNS
Nonlinear Nonparametric Statistics
remicres/otbtf
Deep learning with otb (mirror of https://forgemia.inra.fr/orfeo-toolbox/otbtf)