A 16-Channel Fully Configurable Neural SoC With 1.52 $\mu$W/Ch Signal Acquisition, 2.79 $\mu$W/Ch Real-Time Spike Classifier, and 1.79 TOPS/W Deep Neural Network Accelerator in 22 nm FDSOI.
Seyed Mohammad Ali ZeinolabedinFranz Marcus SchüffnyRichard GeorgeFlorian KelberHeiner BauerStefan ScholzeStefan HänzscheMarco StolbaAndreas DixiusGeorg EllguthDennis WalterSebastian HöppnerChristian MayrPublished in: IEEE Trans. Biomed. Circuits Syst. (2022)
Keyphrases
- neural network
- real time
- signal acquisition
- network architecture
- spiking neurons
- fuzzy artmap
- learning vector quantization
- neural model
- neural fuzzy
- feature set
- artificial neural networks
- high speed
- multi layer perceptron
- pattern recognition
- neuron model
- backpropagation neural network
- associative memory
- neural network model
- low cost
- training data
- spike trains
- parallel implementation
- back propagation
- support vector machine
- learning algorithm
- learning rules
- data acquisition
- hebbian learning
- signal processing
- low power
- monitoring system