Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
Repository Index
132,241 visible repositories in the index
1–4 of 4 · Most stars
Layers Outputs and Gradients in Keras. Made easy.
- keras
- keras-neural-networks
- keras-tutorials
- keras-visualization
This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learnable non linear activations in each pixel.
Inspect, visualize and intervene on any operation in any neural network. Capture every activation and gradient, the full computational graph and 800+ metadata fields without changing model code. Supports PyTorch, JAX, TensorFlow, MLX, PaddlePaddle and tinygrad. Validated on 6400+ models. Built for researchers and their AI agents.
- activations
- computational-graph
- deep-learning
- explainable-ai