New C implementations of Clifford neural network layers run up to 30% faster than the reference PyTorch library on a single CPU core.
Fast Clifford Neural Layers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Clifford Neural Layers improve PDE modeling by introducing Clifford Algebra into neural networks. In this project we focus on optimizing the inference of 2/3D Clifford convolutional layers and multivector activation layers for one core CPU performance. Overall, by testing on a real network block involving Clifford convolutional layers and multivector activation layers, we observe that our implementation is 30% faster than standard PyTorch implementation in relatively large data + network size (>L2 cache). We open source our code base at https://github.com/egretwAlker/c-opt-clifford-layers
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fast Clifford Neural Layers
New C implementations of Clifford neural network layers run up to 30% faster than the reference PyTorch library on a single CPU core.