Low-power platform for edge biometrics launched by Synaptics and Eta Compute
Synaptics Inc. announced its newest battery-powered edge computing platform Katana Edge AI in partnership with Eta Compute to enable on-device face biometrics. The new platform combines low power SoC architecture with energy-efficient AI software and is aimed at consumer and IoT applications.
Katana can make ordinary surveillance systems capable of object and facial recognition and provides various ultra-low power edge devices for use cases in offices, retail stores, factories, farms, and smartphones, the companies say. Other applications include voice biometrics and sound detection, counting and inventory tracking, as well as environmental sensing.
“Today, there is a growing demand for edge intelligence in devices that perform video-, audio-, or voice-based detection and classification. However, there are significant gaps in the availability of power-efficient solutions and the expertise to effectively program them,” said Satish Ganesan, chief strategy officer at Synaptics. “The combination of Synaptics’ Katana platform and Eta Compute’s TENSAI flow software addresses these gaps while significantly growing our opportunity in a multi-billion-dollar market.”
The platform can be combined with Synaptics’ wireless products to provide comprehensive system-level modules and solutions. Katana runs on an ultra-low powered multi-core processor combining efficiency and speed. The system’s optimized neural network and domain-specific processing cores promise versatile operational modes while providing power efficiency and maximum chip memory utilization.
Eta Compute’s TENSAI Flow promises to be the most power-efficient Edge AI Software
Addressing the growing demand for efficiency in battery-operated devices, Eta Compute’s TENSAI Flow software will allow Synaptics to combine the industry’s most efficient AI compiler with a wide set of performance and power-optimized libraries.
“The combination of Synaptics’ ultra-low-power silicon and Eta Compute’s power- and cost-optimized software will become a catalyst for customer innovation,” said Dr. Ted Tewksbury, CEO of Eta Compute. “Together, the optimized solution will enable the proliferation of AI edge inferencing in a wide range of existing applications, as well as new applications that were never thought to be possible.”
Eta Compute and Synaptics will also provide application-focused SDKs that accelerate development and deployment. While users will be able to train the models using their own datasets by industry-standard frameworks such as TensorFlow, Caffe, and ONNX, the kits will also contain reference designs and pre-trained machine learning models and reference designs.
Synaptics leads $12.5M funding round and places CSO on Eta board
Eta Compute has also closed a $12.5 million Series C funding round led by Synaptics and with participation from existing investors.
The funding brings Eta to $31.9 million in total, and will support the company’s expanded focus into ready-to-deploy system-level solutions like those it is partnering with Synaptics on. Synaptics Chief Strategy Officer Satish Ganesan will join Eta’s Board of Directors.
“We are delighted and privileged to have Satish as the newest member of the Eta Compute board,” said Dr. Ted Tewksbury, CEO of Eta Compute. “He brings a wealth of strategic, business and technology experience and we look forward to collaborating with Synaptics to address the multi-billion dollar opportunity in Edge AI.”