Neuromorphic test chip for Tiny AI
POLYN Technology as announced that its first Neuromorphic Analog Signal Processor (NASP) chip is packaged and evaluated, demonstrating proof of the technology’s brain-mimicking architecture. It is the first Tiny AI true analog design to be used next to sensors.
POLYN Technology is an innovative provider of ultra-low-power-performance NASP technology and a producer of unique Tiny AI chips and their associated IP.
“This achievement validates the intensive work of our multinational team,” said Aleksandr Timofeev, CEO and founder of POLYN Technology. “Our chip represents the most advanced technology bridging analog computations and the digital core. It is designed with neuroscience in mind, replicating pre-processing the primary cortical area of the human brain does at the periphery before learning at the center.”
The NASP chip enables full data processing disaggregation between the sensor node and the cloud. NASP is a true Tiny AI product targeted for raw data optimization and reducing the CPU load and amount of data forwarded to the cloud. The NASP chip is located right next to a sensor, forming the Tiny AI logical layer. It is an inference engine that uses already trained machine-learning models to make predictions.
Based on POLYN’s years of expertise, the “inference-only” approach is highly efficient for applications such as voice extraction, sound/vibration processing, measurements on wearables and more. It provides a huge advantage in power, accuracy, and latency.
The NASP test chip contains several neural networks. The chip is implemented in 55nm CMOS technology. Its design proves the NASP “neuron” model as well as the scalability of the technology and efficiency of the chip design automation tools developed by POLYN.
“Our first chip is created from trained neural networks by NASP Compiler and synthesis tools that generated Netlist and the silicon engineering files from the software math model simulation. We will continue to refine our technology for creation of new generation chips,” said Yaakov Milstain, COO of POLYN.
The main advantage of neural network computing is parallel operation. The top advantage is neuromorphic computing, especially geared for maximum parallelism through hardware and software design that strives to mimic the human brain and achieve its compute-to-power-consumption efficacy. Besides low power consumption and improved performance of computing workloads, neural networks provide fault tolerance, which means the system can still produce results if a sensor data is inconsistent.
All sensor signals entering the input layer of the NASP chip at the same time are transmitted to the successive layers in parallel. There are no execution cycles, and no instructions directed to/from memory.
POLYN anticipates the chip will be available to customers in the first quarter of 2023 as its first wearables product, with a fusion of PPG and IMU sensors for the most accurate heart rate measurement along with recognition and tracking of human activity.