Femtosense Secures Capital Investment to Drive Development of AI-Powered Consumer Electronics
While large AI systems like OpenAI’s GPT-3 may grab headlines, the practical limitations of power consumption and cost often determine where AI is deployed. For the most part, highly capable systems are relegated to the cloud because they’re too complex to run on edge devices with weaker hardware and limited connectivity.
The Edge Hardware Challenge
Sam Fok laments this state of affairs. He’s the CEO of Femtosense, a startup developing edge hardware designed to make AI processing viable for low-cost consumer electronics. Founded by members of the ‘Brains in Silicon’ group at Stanford, which seeks to reverse-engineer how the brain uses relatively little data to learn, Femtosense aims to tackle use cases like noise suppression and speech enhancement for hearing aids and earbuds as well as security cameras, TVs, and cars.
Addressing the Hardware-Algorithm Gap
Femtosense is unique in being intentional about developing both hardware and algorithms that push the hardware and algorithm design space into sparse computing, which has yet to be exploited while still working well with existing technology. Fok explains:
‘Hardware developers still build new hardware for existing workloads, and algorithm developers optimize for existing hardware. There’s an inherent bias in what gets built towards what exists. Femtosense is fairly unique in being intentional to develop both hardware and algorithms that push the hardware and algorithm design space into sparse computing that has yet to be exploited while still working well with existing technology.’
The SPU-001: A New Generation of Edge Hardware
Femtosense’s first-generation processor, the SPU-001, hasn’t begun demoing yet, and mass production is at least several months off (sometime in 2023). However, Fok claims that it will enable product developers to run 10 MB AI models at the power it normally takes to run 100 KB models. The size of an AI model usually corresponds to sophistication; smaller models tend to be less accurate.
Real-World Applications
Fok explains that a company using the SPU-001 could run an AI-based noise cancellation algorithm that, when merged with applications like speech-to-text, delivers an improved user experience (think a voice-controlled TV remote that can better understand you in loud surroundings). Such a setup could also drive personalization, for instance:
‘Imagine being able to adjust the volume of your music based on the ambient noise level in your environment. That’s what our technology is capable of achieving.’
Market Opportunity
The market opportunity for Femtosense is vast, with applications in various industries such as consumer electronics, automotive, and healthcare. The company’s focus on edge hardware and sparse computing positions it well to address the limitations of current AI systems.
Funding and Growth
Femtosense has secured funding from top-tier investors, which will enable the company to accelerate its development and commercialization efforts. With a strong management team and a clear vision for the future, Femtosense is poised to become a leading player in the edge AI market.
