A fast, effective data attribution method for neural networks in PyTorch
-
Updated
Jun 7, 2024 - Python
A fast, effective data attribution method for neural networks in PyTorch
Official repository of our work "Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning" accepted at CVPR 2024
TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels
Code accompanying the paper "On the adaptation of recurrent neural networks for system identification"
We propose a lossless compression algorithm based on the NTK matrix for DNN. The compressed network yields asymptotically the same NTK as the original (dense and unquantized) network, with its weights and activations taking values only in {0, 1, -1} up to scaling.
Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural network models (and their initializations) to make them easier to train.
TF2 Implementation of Physics Informed Neural Networks and Neural Tangent Kernel
Official Code: Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes
Implementation of Approximate Smooth Kernel Value Iteration
Code for "Learnware Reduced Kernel Mean Embedding Specification Based on Neural Tangent Kernel"
Neural Tangent Kernel (NTK) module for the scikit-learn library
Add a description, image, and links to the neural-tangent-kernel topic page so that developers can more easily learn about it.
To associate your repository with the neural-tangent-kernel topic, visit your repo's landing page and select "manage topics."