Brainchip Holdings (ASX:BRN) has signed a US$1.8 million contract with the U.S. Air Force Research Laboratory (AFRL) to develop neuromorphic radar signal processing algorithms. The contract is part of the Small Business Innovation Research Programme.

The total contract amount is payable over a 12-month contract period.

technology

BrainChip specializes in developing “neuromorphic” computing. Unlike traditional processors (such as CPUs and GPUs) that process information sequentially, neuromorphic processors aim to mimic the functions of the brain.

BrainChip’s flagship product is the Akida 2.0 processor, which is used in military, self-driving cars, consumer electronics, and industrial IoT applications. The chips allow these devices to process data themselves (known as “edge computing”) rather than sending it to cloud servers. This approach reduces response time, improves privacy, and significantly reduces energy consumption.

Traditional AI models require large pre-trained neural networks. To “train” it to recognize patterns, you need to feed it a huge dataset. In contrast, the Akida 2.0 chip enables continuous learning and can adapt to new data on the fly. This is especially useful in dynamic environments.

The TENN (Temporal Event Neural Network) algorithm framework is designed to work with Akida and is focused on time-based data processing, making it excellent for processing video, audio, radar, and sensor data.

Contract details

This project will focus on developing and optimizing radar processing algorithms for BrainChip’s proprietary hardware.

The SBIR contract, titled “Mapping Complex Sensor Signal Processing Algorithms onto Neuromorphic Chips,” demonstrates the feasibility for multinational aerospace and defense customers to run radar processing algorithms on BrainChip hardware. Based on previous research.

The current contract will apply this research to a specific type of radar processing known as micro-Doppler signature analysis, which allows researchers to identify different types of activity by analyzing subtle movement patterns. It will be. For example, this process can detect whether a person is walking, running, or standing still.

This capability has potential applications in military, robotics, and space-based platforms.

The stock closed yesterday at 24 cents, up 11.36%.