Training convolutional networks of threshold neurons suited for low-power hardware implementation.
Johannes FieresJohannes SchemmelKarlheinz MeierPublished in: IJCNN (2006)
Keyphrases
- low power
- hardware implementation
- power consumption
- low cost
- high speed
- single chip
- software implementation
- low power consumption
- field programmable gate array
- efficient implementation
- signal processing
- image processing algorithms
- dedicated hardware
- neural network
- digital signal processing
- fpga implementation
- high power
- mixed signal
- logic circuits
- vlsi circuits
- hidden layer
- power reduction
- cmos technology
- fpga technology
- vlsi architecture
- processing elements
- multi channel
- belief propagation
- image quality
- machine learning