BrainChip Unveils Communication Reference Platform, Fueling Signal Intelligence at the Edge

Rhea-AI Impact

(Neutral)

Rhea-AI Sentiment

(Neutral)

Key Terms

neuromorphic technical

Neuromorphic describes computer hardware and software designs that mimic the brain’s structure and signaling to process information more efficiently, often using networks of artificial “neurons” and event-driven signals rather than traditional step-by-step computing. Investors care because neuromorphic systems can offer big gains in speed and energy use for tasks like pattern recognition and edge devices, potentially enabling new products, lower operating costs, and competitive advantage in AI-driven markets.

digital signal processing technical

Digital signal processing is the use of computer algorithms to clean up, compress, analyze and transform raw electronic signals from sensors, microphones, cameras or other devices into useful information. For investors, it matters because these algorithms determine product performance, reliability, power use and cost—factors that affect a company’s competitiveness, customer satisfaction and regulatory compliance much like a quality engine shapes a car’s value and appeal.

signal-to-noise ratio technical

The signal-to-noise ratio measures how much useful information (the signal) stands out from irrelevant or random data (the noise). For investors, a high ratio means price moves, earnings reports or research reliably reflect real value or trends, while a low ratio means it's harder to separate meaningful signals from meaningless fluctuations—like trying to hear a single voice in a crowded room or tune a radio to a clear station, which affects confidence in decisions.

software-defined radio technical

A software-defined radio is a radio system where functions traditionally done by fixed hardware—like tuning, filtering and decoding signals—are performed by software running on general-purpose processors. For investors, it matters because this flexibility can cut development costs, speed product updates, expand applications across markets, and concentrate value in software and services rather than specialized chips, while also raising considerations about regulatory compliance and cybersecurity.

See more from StockTitan in Google Search and AI answers. Adds StockTitan as a preferred source · opens Google

Add on Google

06/23/2026 - 09:00 AM

LAGUNA HILLS, Calif.--(BUSINESS WIRE)-- BrainChip Holdings Ltd. (ASX: BRN, OTCQX: BRCHF, BCHPY), the first commercial producer of neuromorphic artificial intelligence technology, today announced the Akida Communication Reference Platform, a physical development platform for RF signal classification using BrainChip’s Akida AKD1500 neuromorphic processor.

The platform is a critical tool for defense contractors and government agencies who need real-time, on-device signal intelligence at the edge but are constrained by power budgets, thermal limits and SWaP-C requirements that GPU- and FPGA-based solutions cannot meet.

The Akida Communications Reference Platform is designed to fuel the exploding demand for on-device signal intelligence worldwide and is a key component of extending BrainChip's core ‘Always-On AI at the Edge’ strategy to RF at the edge.

Akida Communications detects RF threats for operators at the edge

The platform provides fully on-device processing for personnel operating in environments where they cannot rely on wired power, large and/or heavy form-factors and cloud server connections for signal classification.

Powered by BrainChip’s Akida AKD1500 chip, the platform delivers sub-watt continuous inference versus multi-watt power consumed by competitive FPGA or GPU-based edge AI modules.

Rule-based digital signal processing (DSP) systems are challenged to adapt to novel or adversarial modulated signals. The Akida model classifies more than 20 modulation types in real time while consuming sub-watt inference power, with an accuracy of greater than 85% accuracy at a signal-to-noise ratio of 30 decibels. As new wireless emitter threats emerge, the platform can capture data of unrecognized waveforms to retrain the model to recognize them, extending the operational utility of the platform to adapt in the field.

This closes a gap left by DSP classifier algorithms that are difficult to adapt, power-hungry and too large for deployment in unmanned aerial vehicles (UAVs), handheld SIGINT devices or satellite terminals.

The platform is ideal to prototype SIGINT applications

Available for evaluation and partner integration, the platform can be used as a hardware reference design kit intended for defense contractors, government agencies, SDR vendors and edge AI system integrators who want to evaluate or prototype neuromorphic AI-based RF signal classification. The platform, which provides real-time threat detection in battery-powered devices, integrates with software-defined radio (SDR) front ends, such as the USRP B205mini or the EPIQ Sidekiq using a host system such as the Raspberry Pi 5 computer. Engineering and product teams can use it to develop custom intelligence, surveillance and reconnaissance functions and SIGINT applications.

“BrainChip's Akida Communication Reference Platform proves that real-time signal intelligence can be condensed into a portable battery powered solution to extend the range of deployment options,” said Sean Hehir, BrainChip’s CEO. “This extends BrainChip's reference platform strategy (alongside radar and other sensor-fusion platforms) to demonstrate that Akida is a broadly applicable edge AI processing engine for many use cases.”

About BrainChip Holdings Ltd.

BrainChip Holdings Ltd. is the worldwide leader in edge AI on-chip processing and learning. The company’s first-to-market, fully digital, event-based AI processor, Akida™, uses neuromorphic principles to mimic the human brain, analyzing only essential sensor inputs at the point of acquisition and processing data with unmatched efficiency, precision and energy economy. BrainChip’s Temporal Event-based Neural Networks (TENNs) build on State-Space Models (SSMs), deliver time-aware, event-driven intelligence optimized for scalable, real-time streaming applications. These innovations make low-power Edge AI deployable across industries such as aerospace, autonomous vehicles, robotics, industrial IoT, consumer devices, and wearables. BrainChip is advancing the future of intelligent computing, bringing AI closer to the sensor and closer to real-time. Explore more at www.brainchip.com.

Follow BrainChip:
Twitter: https://www.twitter.com/BrainChip_inc
LinkedIn: https://www.linkedin.com/company/7792006