Neuromorphic Analog Signal Processing (NASP)
Sensor level platform to synthesize a true neuromorphic Tiny AI chip layout from any trained neural network
NASP Technology is ideal for real time EDGE sensor signal processing (ESSP) appliances, providing small size, ultra-low power consumption and low lattency
NASP Convertor works with any standard Neural Net framework like Keras, TensorFlow or others
NASP receives any type of signals and processes raw sensor data using neuromorphic AI computations on sensor level without digitalizing analog signals
1Direct analog /digital signal input
2POLYN’s neuromorphic architecture processes input signals in a true parallel, asynchronous mode, which provides unprecedented low latency and low power consumption. Calculations do not require CPU usage or memory access.
3NASP can use a pre-trained artificial neural network from any major ML framework (such as TensorFlow, PyTorch, MXNet etc) for the neuromorphic representation resulting in exceptional precision and accuracy.
- NN is provided by customer or Polyn assists the customer in NN selection
- Fully functionable math model of NN
- Data set collection and training process
- Accept of final functionality of trained NN
- Convert trained NN to Netlist for CAD and generate neurons library
- Build CAD model of NASP block
- Verification of NASP CAD model and NN model conformity
- Generate final layout and GDSII format for target Node and Fab