We want to hear from you! Take our quick AI survey and share your insights on the current state of AI, how you're implementing it, and what you expect to see in the future. learn more
While much of the tech world is stuck with the latest big language models powered by Nvidia GPUs, a quiet revolution is taking place in AI hardware. As the limitations and energy requirements of traditional deep learning architectures become increasingly apparent, a new paradigm is emerging called neuromorphic computing – an attempt to reduce the computational and power requirements of AI by orders of magnitude. promises
Mimicking Nature's Masterpiece: How Neuromorphic Chips Work.
But what exactly are neuromorphic systems? To find out, I spoke to Sumit Kumar, CEO and founder of Inatera, a leading startup in the neuromorphic chip space.
“Neuromorphic processors are designed to mimic the way the biological brain processes information,” Kumar explained. “Instead of performing sequential operations on data stored in memory, neuromorphic chips are networks of artificial neurons. use neurons that communicate via spikes like real neurons.”
This brain-inspired architecture gives neuromorphic systems distinct advantages, especially for edge computing applications in consumer devices and industrial IoT. Kumar highlighted several compelling use cases, including always-on audio processing for voice activation, real-time sensor fusion for robotics and autonomous systems, and ultra-low-power computer vision.
Countdown to VB Transform 2024
Join enterprise leaders in San Francisco July 9-11 for our flagship AI event. Connect with peers, explore the opportunities and challenges of generative AI, and learn how to integrate AI applications into your industry. Register now
“Importantly, neuromorphic processors can perform complex AI tasks using a fraction of the energy of traditional solutions,” noted Kumar. “This enables capabilities like continuous environmental awareness in battery-powered devices that weren't possible before.”
From doorbell to data center: Real-world applications emerge.
Inatera's flagship product, the Spiking Neural Processor T1, released in January 2024, exemplifies these benefits. T1 combines an event-driven computing engine with a traditional CNN accelerator and RISC-V CPU, creating a comprehensive platform for ultra-low-power AI in battery-powered devices.
“Our neuromorphic solutions can perform computing with 500 times less energy than conventional methods,” Kumar said. “And we're seeing pattern recognition speeds nearly 100 times faster than competitors.”
Kumar illustrates this point with a compelling real-world application. Inatera has partnered with Socionext, a Japanese sensor vendor, to develop an innovative solution for human presence detection. The technology, which Kumar demonstrated at CES in January, combines a radar sensor with Inatera's neuromorphic chip to create highly efficient, privacy-preserving devices.
“Take video doorbells, for example,” Kumar explained. “Traditional ones use power-hungry image sensors that need to be charged frequently. Our solution uses a radar sensor, which is much more energy efficient. The system can detect human presence here. As long as a person is motionless, as long as their heart is beating, it preserves privacy until the camera needs to be activated.
The technology has a wide range of applications beyond doorbells, including smart home automation, building security, and even vehicle occupancy detection. “This is a great example of how neuromorphic computing can transform everyday devices,” noted Kumar. “We're actually bringing AI capabilities to the forefront while reducing power consumption and increasing privacy.”
Doing more with less in AI compute
These dramatic improvements in energy efficiency and speed are driving significant industry interest. Kumar revealed that Inatera has a number of customer engagements underway, with traction for neuromorphic technologies continuing to grow. The company is targeting the sensor edge applications market with an ambitious goal of bringing intelligence to one billion devices by 2030.
To meet this growing demand, Inatera is ramping up production. The spiking neural processor is scheduled to enter production later in 2024, with high-volume deliveries beginning in the second quarter of 2025. This timeline reflects the rapid progress the company has made since being spun out of Delft University of Technology in 2018. In just six years, Inatera has grown to nearly 75 employees and recently appointed former Apple VP Duco Pasmooij to its advisory board.
The company recently closed a $21 million Series A round to accelerate development of its spiking neural processors. The round, which was subscribed to, included investors like Innavest, InvestNL, EIC Fund, and MIG Capital. This strong investor backing underscores the growing excitement around neuromorphic computing.
Kumar envisions a future where neuromorphic chips increasingly handle AI workloads at the edge, while larger underlying models reside in the cloud. “There's a natural complement,” he said. “Neuromorphics excel at fast, efficient processing of real-world sensor data, while large language models are better suited for reasoning and knowledge-intensive tasks.”
“It's not just about raw computing power,” Kumar observed. “The brain achieves remarkable feats of intelligence with a fraction of the energy that our current AI systems require. This is the promise of neuromorphic computing — AI that is not only more capable, but dramatically more efficient.”
Seamless integration with existing tools
Kumar emphasized one key factor that could accelerate the adoption of his neuromorphic technology: developer-friendly tools. “We've built a very comprehensive software development kit that allows application developers to easily target our silicon,” Kumar explained.
Inatera's SDK uses PyTorch as a frontend. “You actually build your neural network entirely in the standard PyTorch environment,” notes Kumar. “So if you know how to build a neural network in PyTorch, you can target our chips.” Can already use the SDK.”
This approach significantly lowers the barrier to entry for developers already familiar with popular machine learning frameworks. This allows them to leverage their existing skills and workflows while tapping into the power and efficiency of neuromorphic computing.
“It's a simple turnkey, standardized, and very fast way to build and deploy applications on our chips,” Kumar added, noting the potential for rapid adoption and integration of Inatera's technology into a wide range of AI applications. Highlighting
The stealth game of Silicon Valley
While major language models grab the headlines, industry leaders are quietly acknowledging the need for radically new chip architectures. Notably, OpenAI CEO Sam Altman, who has been vocal about the rapid arrival of artificial general intelligence (AGI) and the need for massive investment in chip manufacturing, personally co-founded another neuromorphic chip startup. Invested in Up Rain.
This movement is telling. Despite Altman's public statements about enhancing existing AI technologies, his investment suggests a recognition that the path to more advanced AI may require a fundamental shift in computing architecture. Neuromorphic computing may be one of the keys to bridging the performance gap that current architectures face.
Bridging the gap between artificial and biological intelligence
As AI permeates every aspect of our lives, the need for more efficient hardware solutions will only increase. Neuromorphic computing represents one of the most exciting frontiers in chip design today, with the potential to enable a new generation of intelligent devices that are more capable and more durable.
While big language models grab the headlines, the real future of AI may lie in chips that think like our own brains. As Kumar said: “We're just scratching the surface of what's possible with neuromorphic systems. The next few years are going to be very exciting.”
As these brain-inspired chips make their way into consumer devices and industrial systems, we may be nearing a new era of artificial intelligence – faster, more efficient, and more akin to the remarkable capabilities of biological brains. is closely aligned.