Distribution-Aware Tensor Decomposition for Compression of Convolutional Neural Networks
NeutralArtificial Intelligence
- and compute
- \widetilde{W}) \Sigma^{1/2}\rVert_F$ where $\Sigma^{1/2}$ is the square root of the covariance matrix of the layer's input and $W$, $\widetilde{W}$ are the original and compressed weights. We propose new alternating least square algorithms for the two most common tensor decompositions (Tucker
— via World Pulse Now AI Editorial System