A Low-Power Hardware Architecture for On-Line Supervised Learning in Multi-Layer Spiking Neural Networks.
Nan ZhengPinaki MazumderPublished in: ISCAS (2018)
Keyphrases
- multi layer
- low power
- hardware architecture
- spiking neural networks
- supervised learning
- high speed
- power consumption
- low cost
- biologically inspired
- neural network
- hardware implementation
- feed forward
- neural nets
- artificial neural networks
- learning rules
- training data
- field programmable gate array
- reinforcement learning
- learning tasks
- biologically plausible
- machine learning
- training set
- associative memory
- semi supervised
- active learning
- image sensor
- learning algorithm
- motor control
- back propagation
- information processing
- cmos technology
- class labels
- signal processing
- pattern recognition
- multiscale
- computer vision
- power dissipation