.png){kind=icon}
返回
Mixed-Precision Continual Learning Based on Computational Resistance Random Access Memory
.png){kind=icon}
OA
AI
DOI：10.1002/aisy.202200026.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Artificial neural networks have acquired remarkable achievements in the field of artificial intelligence. However, it suffers from catastrophic forgetting when dealing with continual learning problems, i.e., the loss of previously learned knowledge upon learning new information. Although several continual learning algorithms have been proposed, it remains a challenge to implement these algorithms efficiently on conventional digital systems due to the physical separation between memory and processing units. Herein, a software-hardware codesigned in-memory computing paradigm is proposed, where a mixed-precision continual learning (MPCL) model is deployed on a hybrid analogue-digital hardware system equipped with resistance random access memory chip. Software-wise, the MPCL effectively alleviates catastrophic forgetting and circumvents the requirement for high-precision weights. Hardware-wise, the hybrid analogue-digital system takes advantage of the colocation of memory and processing units, greatly improving energy efficiency. By combining the MPCL with an in situ fine-tuning method, high classification accuracies of 94.9% and 95.3% (software baseline 97.0% and 97.7%) on the 5-split-MNIST and 5-split-FashionMNIST are achieved, respectively. The proposed system reduces approximate to 200 times energy consumption of the multiply-and-accumulation operations during the inference phase compared to the conventional digital systems. This work paves the way for future autonomous systems at the edge.
Keyword:
continual learning
in-memory computing
mixed precision
resistance random access memory
期刊
IF:
6.1
论文数:
2.0K
被引数:
8.4K
机构
引用论文
Nutritional Status Affects Treatment Tolerability and Survival in Metastatic Colorectal Cancer Patients: Results of an AGEO Prospective Multicenter Study营养状况影响转移性结直肠癌患者的治疗耐受性和生存率: 一项AGEO前瞻性多中心研究的结果.png)
Oncology
OncologyIF0
PREAI
分享收藏分享收藏In situ click chemistry generation of cyclooxygenase-2 inhibitorscyclooxygenase-2抑制剂的原位点击化学生成NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏U1 snRNP regulates cancer cell migration and invasion in vitroU1 snRNP体外调控癌细胞迁移和侵袭NATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏Fabrication of porous hollow γ-Al2O3 nanofibers by facile electrospinning and its application for water remediation静电纺丝法制备多孔中空 γ-Al2O3纳米纤维及其在水体修复中的应用
PREAI
分享收藏Memory devices and applications for in-memory computing用于内存计算的内存设备和应用NATURE NANOTECHNOLOGYOAAI
NATURE NANOTECHNOLOGYIF34.9
OAAI分享收藏
查看更多内容