An Approximate Memory Architecture for a Reduction of Refresh Power Consumption in Deep Learning Applications.
Duy Thanh NguyenHyun KimHyuk-Jae LeeIk Joon ChangPublished in: ISCAS (2018)
Keyphrases
- power consumption
- deep learning
- nm technology
- power management
- low power
- power reduction
- power dissipation
- unsupervised learning
- power saving
- machine learning
- energy efficiency
- unsupervised feature learning
- multithreading
- energy saving
- cmos technology
- battery life
- real time
- data center
- management system
- data mining
- memory management
- reinforcement learning