Back to Search
Start Over
LTNN: A Layerwise Tensorized Compression of Multilayer Neural Network.
- Source :
-
IEEE Transactions on Neural Networks & Learning Systems . May2019, Vol. 30 Issue 5, p1497-1511. 15p. - Publication Year :
- 2019
-
Abstract
- An efficient deep learning requires a memory-efficient construction of a neural network. This paper introduces a layerwise tensorized formulation of a multilayer neural network, called LTNN, such that the weight matrix can be significantly compressed during training. By reshaping the multilayer neural network weight matrix into a high-dimensional tensor with a low-rank approximation, significant network compression can be achieved with maintained accuracy. An according layerwise training is developed by a modified alternating least-squares method with backward propagation for fine-tuning only. LTNN can provide the state-of-the-art results on various benchmarks with significant compression. For MNIST benchmark, LTNN shows $64 \times $ compression rate without accuracy drop. For Imagenet12 benchmark, our proposed LTNN achieves $35.84 \times $ compression of the neural network with around 2% accuracy drop. We have also shown $1.615 \times $ faster on inference speed than the existing works due to the smaller tensor core ranks. [ABSTRACT FROM AUTHOR]
- Subjects :
- *ARTIFICIAL neural networks
*DEEP learning
*DATA compression
Subjects
Details
- Language :
- English
- ISSN :
- 2162237X
- Volume :
- 30
- Issue :
- 5
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Neural Networks & Learning Systems
- Publication Type :
- Periodical
- Accession number :
- 136117589
- Full Text :
- https://doi.org/10.1109/TNNLS.2018.2869974