Stochastic Learning with Back Propagation
- Title
- Stochastic Learning with Back Propagation
- Author
- 정두석
- Keywords
- Stochastic learning with backpropagation; Ternary weight; Crossbar array; Denoising autoencoder
- Issue Date
- 2019-05
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Citation
- 2019 IEEE International Symposium on Circuits and Systems (ISCAS) , Page. 1-5
- Abstract
- Despite of remarkable progress on deep learning, its hardware implementation beyond deep learning acceleration is still behind the software deep learning due in part to lack of hardware-compatible learning algorithm. In this paper, a learning method called the stochastic learning with backpropagation (SLBP) algorithm was proposed. The network of concern consists of ternary synaptic weight, favorable to be implemented in a resistance-based crossbar array. Every training epoch, the SLBP algorithm evaluates weight update probability at which the corresponding weight is updated in a stochastic manner. The algorithm was used to train a denoising autoencoder, which identified the successful reduction in noise (increase in peak signal-to-noise ratio by approximately 68%). Notably, the SLBP algorithm achieves an 86% reduction in memory usage compared with a real-valued autoencoder trained using a backpropagation algorithm.
- URI
- https://ieeexplore.ieee.org/document/8702253https://repository.hanyang.ac.kr/handle/20.500.11754/151268
- ISBN
- 978-172810397-6
- ISSN
- 0271-4310; 2158-1525
- DOI
- 10.1109/ISCAS.2019.8702253
- Appears in Collections:
- COLLEGE OF ENGINEERING[S](공과대학) > MATERIALS SCIENCE AND ENGINEERING(신소재공학부) > Articles
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML