DOING MORE
with less
Empowering the next generation
of smart devices.
Our breakthrough neuromorphic chip processes AI workloads using less than 1 µW through a fully analog pipeline from sensor to chip. Doing more with less isn't just our motto; It's empowering the next generation of smart devices.
OUR INVESTORS
.png)
.png)
VISION
A NEW CLASS
of intelligent sensors
AI systems excel at processing large volumes of static data, such as text and tables. But the real world doesn’t generate static data; it generates temporal data through analog sensors that continuously capture dynamic, real-time signals. And that’s where today’s hardware falls short.
We don’t need edge chips that mimic miniature versions of cloud architectures at the edge.
We need a new class of chips, purpose-built to process sensor data at the source, with architectures designed to understand time.
Our proprietary processor combines
in-memory computing with the physical implementation
of spiking neurons and synapses using analog circuits.
This approach enables us to implement full networks in hardware, with the natural ability to process temporal information in real time, and with extremely low energy consumption.
You can really do more
with less
Artificial neural networks running on conventional digital hardware require hundreds of thousands of parameters to handle temporal tasks, such as keyword recognition ("Hey Neuronova!").
Our networks achieve the same accuracy while consuming up to 1000x less power and usingonly a few hundred parameters.
A fully analog pipeline
Future sensors will be intelligent and programmable, with adaptive front ends that can offset sensor drift and non-ideality but also solve complex tasks without the need of a micro-controller. We are working on sensor integration to bring our chip in the package of every sensor.
.png)
Towards full sensor integration
Future sensors will be intelligent and programmable, with adaptive front ends that can offset sensor drift and non-ideality but also solve complex tasks without the need for a microcontroller. We are working on sensor integration to
bring ourchip in the package of every sensor.
You can really do more
with less
Conventional digital neural networks for temporal tasks (e.g. wake word detection “Hey Neuronova!”) typically require ~100,000 parameters. Our analog neuromorphic approach achieves the same accuracy with only ~1000 parameters, not by compressing the model, but by using a fundamentally different form of computation in the analog and time domain. This is a true paradigm shift in how neural networks are implemented.
A fully analog pipeline
Analog to digital conversion (ADC) can be expensive for low power systems, with always-on computation requiring data buffering and data movements before computation on the microcontroller. Our fully analog pipeline avoids ADC and only send information to the MCU when necessary.
Towards full sensor integration
Future sensors will be intelligent and programmable, with adaptive front ends that can offset sensor drift and non-ideality but also solve complex tasks without the need of a micro-controller. We are working on sensor integration to bring our chip in the package of every sensor.
You can really do more with less
Conventional digital neural networks for temporal tasks (e.g. wake word detection “Hey Neuronova!”) typically require ~100,000 parameters. Our analog neuromorphic approach achieves the same accuracy with only ~1000 parameters, not by compressing the model, but by using a fundamentally different form of computation in the analog and time domain. This is a true paradigm shift in how neural networks are implemented.
A fully analog pipeline
Future sensors will be intelligent and programmable, with adaptive front ends that can offset sensor drift and non-ideality but also solve complex tasks without the need of a micro-controller. We are working on sensor integration to bring our chip in the package of every sensor.
Towards full sensor integration
Future sensors will be intelligent and programmable, with adaptive front ends that can offset sensor drift and non-ideality but also solve complex tasks without the need of a micro-controller. We are working on sensor integration to bring our chip in the package of every sensor.
doing more with less
TECHNOLOGY
H1
Our most advanced processor to date, a fully analog chip for Spiking Neural Networks on the EDGE.
Programmable analog neurons and synapses with a configurable analog front-end
Ready-to-use weights for typical applications
API for easy deployment of networks
Digital output with standard communication protocol (SPI)
4
Analog
Cores
28k
Programmable Synapses
180nm
Standard CMOS Process
<1uW
Power
Consumption
USE CASES
OUR SOLUTION
to real world
problems
Keyword
Spotting
Continuous keyword recognition that operates at microwatt power levels, perfect for battery-powered IoT devices, smart devices, and wearables.
Wake word Detection
Always-listening voice activation that triggers your device from sleep mode with ultra-low latency, enabling hands-free operation for voice assistants, smart home systems, and automotive interfaces while preserving battery life.
Direction
of Arrival
Enable devices to precisely locate sound sources in real-time, powering superior voice enhancement and noise cancellation in multi-microphone systems.
Sensor Drift Compensation
Eliminate the need for constant sensor recalibration with adaptive frontends that automatically compensate for drift, maintaining precision over time.
Denoising
Remove background noise from single-microphone recordings in real-time, delivering clean audio even in challenging environments.
Biosignal
& IMU
Decode intentions and gestures from EMG and IMU data. Monitor user health continuously with always-on smart monitoring of PPG and ECG.
EVALUATION KIT
Try our
TECHNOLOGY
Evaluation board: Silk 1
Evaluation board: Silk 1
-
USB-C & BLE
-
STM Microcontroller onboard (STM32H755ZIT)
-
API for simple deployment
-
Arduino R1 connector for sensor expansion boards
USB-C & BLE
STM Microcontroller onboard (STM32H755ZIT)
API for simple deployment
Arduino R1 connector for sensor expansion boards
Expansion shield: Microphones
ONBOARD MICROPHONES
TDK ICS-40212
STM IMP232ABSU
Knowles MM20-33366
Knowles MM25-33663
TDK ICS-40212
STM IMP232ABSU
Knowles MM20-33366
Knowles MM25-33663
doing more with less
OUR TEAM
MEET THE PEOPLE
behind our Company
Alessandro Milozzi
CEO & Co-Founder
Michele Mastella
CTO & Co-Founder
Marco Rasetto
Head Of AI & Co-Founder
Giorgio Ferrari
Scientific Advisor
Federico Currao
Electronic Engineer
Florin Ciobanu
Electronic Engineer
Giuseppe Gentile
ML Engineer
Ilenia Marciano
Neuromorphic Engineer
Luca Beltrame
Founders Associate
Nicolò Caporale
Applied SNN Engineer
doing more with less
PLANS