jloveric / high-order-layers-torch
High order and sparse layers in pytorch. Lagrange Polynomial, Piecewise Lagrange Polynomial, Piecewise Discontinuous Lagrange Polynomial (Chebyshev nodes) and Fourier Series layers of arbitrary order. Piecewise implementations could be thought of as a 1d grid (for each neuron) where each grid element is Lagrange polynomial. Both full connecte…
☆42Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for high-order-layers-torch
- A State-Space Model with Rational Transfer Function Representation.☆70Updated 6 months ago
- Code repository of the paper "Clifford-Steerable Convolutional Neural Networks"☆40Updated 3 months ago
- C++ and Cuda ops for fused FourierKAN☆73Updated 6 months ago
- ☆76Updated 5 months ago
- Kolmogorov-Arnold Networks with various basis functions like B-Splines, Fourier, Chebyshev, Wavelets etc☆31Updated 6 months ago
- Kolmogorov–Arnold Networks with modified activation (using MLP to represent the activation)☆103Updated 3 weeks ago
- Diffusion models in PyTorch☆87Updated last month
- Kolmogorov-Arnold networks (KAN) as implicit functions (like NeRF but simpler)☆13Updated 6 months ago
- Benchmark for efficiency in memory and time of different KAN implementations.☆111Updated 2 months ago
- This code implements a Radial Basis Function (RBF) based Kolmogorov-Arnold Network (KAN) for function approximation.☆25Updated 5 months ago
- TopoBenchmark is a Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning☆85Updated this week
- Official repository of Implicit Neural Convolutional Kernels for Steerable CNNs, Zhdanov et al.☆26Updated 8 months ago
- A simple example of VAEs with KANs☆12Updated 6 months ago
- ☆100Updated this week
- The official repository for HyperZ⋅Z⋅W Operator Connects Slow-Fast Networks for Full Context Interaction.☆31Updated 2 months ago
- An easy to use PyTorch implementation of the Kolmogorov Arnold Network and a few novel variations☆159Updated 3 months ago
- Free-form flows are a generative model training a pair of neural networks via maximum likelihood☆36Updated 5 months ago
- Kolmogorov-Arnold Networks (KAN) using orthogonal polynomials instead of B-splines.☆30Updated 6 months ago
- ☆15Updated 2 years ago
- Official Implementation of the ICML 2023 paper: "Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally …☆69Updated last year
- Code repository for Trajectory Flow Matching☆24Updated 3 weeks ago
- ☆46Updated last month
- Recursive Leasting Squares (RLS) with Neural Network for fast learning☆52Updated last year
- ☆37Updated 6 months ago
- Benchmarking and Testing FastKAN☆65Updated 5 months ago
- Variations of Kolmogorov-Arnold Networks☆111Updated 6 months ago
- Kolmogorov-Arnold Networks (KAN) using Chebyshev polynomials instead of B-splines.☆347Updated 6 months ago
- ☆128Updated this week
- Repo to the paper "Lie Point Symmetry Data Augmentation for Neural PDE Solvers"☆48Updated last year
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆120Updated last year