Neuronovatech provides a fully analog neuromorphic processor that runs spiking neural networks directly on sensor data, delivering real‑time temporal analysis with sub‑microwatt power consumption. By implementing in‑memory computing on the analog front‑end, the chip extracts meaningful events before digital conversion, allowing IoT and edge‑AI devices to maintain always‑on perception while waking the main system only when needed. The solution is offered as a silicon‑validated processor, evaluation kits, and a calibrated SDK for rapid integration.
Funding
$1.6M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
CVTFounders
Product
Problem
Continuous sensor streams such as audio, vibration, motion, and biosignals require always‑on processing, but digital and mixed‑signal architectures consume a baseline amount of power that limits battery life and scalability for edge devices.
Solution
Neuronovatech offers a fully analog neuromorphic processor that implements spiking neurons and synapses directly in hardware, allowing sensor data to be processed in situ before any digital conversion. By performing in‑memory computing on the analog front‑end, the chip extracts meaningful events with sub‑microwatt power consumption, waking the main system only when necessary. This “Analog‑to‑Information™” layer provides real‑time temporal analysis with up to 1000× lower energy use while maintaining comparable accuracy to conventional deep‑learning models. The solution is delivered as a silicon‑validated processor, an evaluation kit, and a calibrated SDK for rapid benchmarking and integration into new sensing‑driven products.
Target Audience
Primary customers are IoT device manufacturers, sensor developers, and edge‑AI system integrators that need ultra‑low‑power, always‑on perception for battery‑operated or remote applications.
Features
- Fully analog spiking neural network implemented in mixed‑signal circuits for real‑time temporal processing
- In‑memory computing architecture that eliminates the digital always‑on power floor
- Sub‑1 µW power envelope for continuous perception on a wide range of analog sensors (audio, vibration, motion, biosignals)
- Supports networks with only a few hundred parameters while achieving accuracy comparable to larger digital models
- Silicon‑validated processor with pre‑order evaluation kits and a silicon‑calibrated SDK for fast benchmarking and development