RistoAle97/centered-kernel-alignment
CKA (Centered Kernel Alignment) implemented in PyTorch
This tool helps machine learning engineers and researchers understand how similar the internal workings of different neural networks are. It takes the layer outputs (representations) from two neural networks and calculates a similarity score, known as Centered Kernel Alignment (CKA). This allows you to compare models and see if they are learning similar features, even if their architectures differ or they are trained on different data.
Use this if you need to quantitatively compare how different neural network models or different layers within a model represent data.
Not ideal if you need a widely supported, production-ready tool for model interpretability, as this project is primarily for personal and academic use and may not work for every model.
Stars
64
Forks
3
Language
Python
License
MIT
Category
Last pushed
Feb 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/RistoAle97/centered-kernel-alignment"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification