A team of German scientists at the Technical University of Munich (TUM) has developed a groundbreaking AI chip modeled after the human brain that performs real-time calculations directly on the spot. Ensuring complete cybersecurity without relying on cloud services or internet connectivity, the chip is poised to revolutionize how devices process and analyze data. The new AI chip, labeled “AI Pro,” was developed under the guidance of Prof.
Hussam Amrouch, PhD, an AI processor design professor at TUM. This one-square-millimeter chip combines memory and processing units in a compact neuromorphic architecture. By mimicking how the human brain processes information, it allows the chip to learn and function independently while consuming up to ten times less energy than conventional AI chips.
Already in the prototype stage and produced by semiconductor manufacturer Global Foundries in Dresden, the chip delivers complete data privacy, exceptional energy efficiency, and true on-device intelligence. Unlike traditional chips, it integrates computing and memory in a single unit, enabling faster, more efficient on-device processing. Amrouch emphasized that the chip achieves this efficiency using an approach that groups and associates different data points to draw inferences.
In simple terms, the chip learns by spotting similarities and patterns, not by processing vast amounts of data. Rather than processing countless images of cars, the chip understands a car by associating it with features like four wheels, road use, and typical shapes. This brain-like thinking also results in significant energy savings; during a trial run, the AI Pro consumed just 24 microjoules, while competing chips consumed between 10 and 100 times more energy.
Ai chip optimizes energy efficiency
This mix of modern processor architecture, algorithm specialization, and innovative data processing makes the AI chip something special,” Amrouch said. The team stated that the AI Pro is tailored for specific applications.
Its architecture tightly integrates memory and processing units, enabling real-time decision-making directly on the spot. This has vast implications for industries like healthcare, robotics, and autonomous navigation, especially in environments where internet access is unreliable or where data privacy is paramount. Smartwatches fitted with the chip could process sensitive heart rate data on the spot, eliminating the need to transmit it to external servers.
Drones could analyze navigation patterns mid-flight without relying on satellite links. Because data stays local, both latency and cybersecurity risks are dramatically reduced. The AI Pro prototype is priced at around $33,700 (€30,000) and is not yet ready for mass production.
However, the team is not concerned about competing with big tech companies. Their goal is to create a new kind of AI chip—one that’s efficient, secure, and built for specific tasks instead of raw power. “There is a huge market there.
The future belongs to the people who own the hardware,” Amrouch concluded.
Kirstie a technology news reporter at DevX. She reports on emerging technologies and startups waiting to skyrocket.
