Sasaki et al., 2019 - Google Patents
Post training weight compression with distribution-based filter-wise quantization stepSasaki et al., 2019
- Document ID
- 6419765911415733700
- Author
- Sasaki S
- Maki A
- Miyashita D
- Deguchi J
- Publication year
- Publication venue
- 2019 IEEE Symposium in Low-Power and High-Speed Chips (COOL CHIPS)
External Links
Snippet
Quantization of models with lower bit precision is a promising method to develop lower- power and smaller-area neural network hardware. However, 4-or lower bit quantization usually requires additional retraining with labeled dataset for backpropagation to improve …
- 238000007906 compression 0 title description 2
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computer systems based on biological models
- G06N3/02—Computer systems based on biological models using neural network models
- G06N3/04—Architectures, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computer systems based on biological models
- G06N3/02—Computer systems based on biological models using neural network models
- G06N3/08—Learning methods
- G06N3/082—Learning methods modifying the architecture, e.g. adding or deleting nodes or connections, pruning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computer systems based on biological models
- G06N3/02—Computer systems based on biological models using neural network models
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Q-vit: Accurate and fully quantized low-bit vision transformer | |
| CN111079781B (en) | Lightweight convolutional neural network image recognition method based on low rank and sparse decomposition | |
| CN113159173B (en) | Convolutional neural network model compression method combining pruning and knowledge distillation | |
| Khashman et al. | Image compression using neural networks and Haar wavelet | |
| CN111147862B (en) | End-to-end image compression method based on target coding | |
| Laha et al. | Design of vector quantizer for image compression using self-organizing feature map and surface fitting | |
| CN112016674A (en) | Knowledge distillation-based convolutional neural network quantification method | |
| CN114970853B (en) | Cross-range quantized convolutional neural network compression method | |
| Sasaki et al. | Post training weight compression with distribution-based filter-wise quantization step | |
| CN112702600B (en) | Image coding and decoding neural network layered fixed-point method | |
| Chen et al. | DNN gradient lossless compression: Can GenNorm be the answer? | |
| CN116976428A (en) | Model training method, device, equipment and storage medium | |
| Ando et al. | Dither nn: An accurate neural network with dithering for low bit-precision hardware | |
| CN108805844B (en) | Lightweight regression network construction method based on prior filtering | |
| Yan et al. | Qnet: an adaptive quantization table generator based on convolutional neural network | |
| Wu et al. | FedComp: A Federated Learning Compression Framework for Resource-Constrained Edge Computing Devices | |
| CN114943335A (en) | Layer-by-layer optimization method of ternary neural network | |
| CN117151178A (en) | FPGA-oriented CNN customized network quantification acceleration method | |
| Liu et al. | Vector quantization in DCT domain using fuzzy possibilistic c-means based on penalized and compensated constraints | |
| Gafour et al. | Genetic fractal image compression | |
| CN110378466A (en) | Quantization method and system based on neural network difference | |
| US20230196095A1 (en) | Pure integer quantization method for lightweight neural network (lnn) | |
| CN114372565B (en) | Target detection network compression method for edge equipment | |
| Huang et al. | Accelerating convolutional neural network via structured gaussian scale mixture models: a joint grouping and pruning approach | |
| Hirose et al. | Quantization error-based regularization for hardware-aware neural network training |