Darkside: 2.6GFLOPS, 8.7mW Heterogeneous RISC-V Cluster for Extreme-Edge On-Chip DNN Inference and Training.
Angelo GarofaloMatteo PerottiLuca ValenteYvan TortorellaAlessandro NadaliniLuca BeniniDavide RossiFrancesco ContiPublished in: ESSCIRC (2022)
Keyphrases
- training process
- low power consumption
- structured prediction
- power consumption
- low cost
- clustering algorithm
- bayesian networks
- edge detection
- high speed
- training examples
- heterogeneous networks
- training samples
- general purpose
- hierarchical clustering
- probabilistic inference
- application specific
- vlsi implementation
- neural network
- cluster analysis
- bayesian inference
- data points
- high density