Low Cost and Low Power Stacked Sparse Autoencoder Hardware Acceleration for Deep Learning Edge Computing Applications.
Tarek BelabedMaria Gracielly F. CoutinhoMarcelo A. C. FernandesCarlos ValderramaChokri SouaniPublished in: ATSIP (2020)
Keyphrases
- low cost
- low power
- deep learning
- restricted boltzmann machine
- single chip
- hardware and software
- unsupervised learning
- low power consumption
- machine learning
- vlsi architecture
- real time
- unsupervised feature learning
- digital signal processing
- digital camera
- embedded systems
- cmos technology
- logic circuits
- mental models
- weakly supervised
- image sensor
- gate array
- high speed
- multiscale
- rfid tags
- video sequences