The latest version of sensai brings new features to low-power and high-performance AI / ml reasoning applications
Shanghai, China – November 18, 2021 – lattice Semiconductor Corporation (NASDAQ: LSCC), a leading supplier of low-power programmable devices, today announced the latest roadmap of its low-power, AI / ml solutions, which can help network edge applications such as client computing devices prolong battery life and bring innovative user experience. They are built from the award-winning collection of lattice sensaitm solutions, which are available in lattice nexus ™ Running on FPGA can help OEM manufacturers develop intelligent, real-time online devices with low power consumption and hardware accelerated AI functions. These devices can also be upgraded on site to support more AI algorithms in the future.
Client computing devices increasingly need fast response and context aware user experience, high-quality video conferencing and collaborative applications. Lattice nexus FPGA and sensai solution set is an ideal platform for developing computer vision and sensor fusion applications, which can enhance user participation and cooperation and protect user privacy. For example, the client device can analyze the image data collected by the camera to determine whether the rear personnel are too close to the user. It can also blur the screen to protect privacy, or darken the screen and prolong the battery life when the user’s attention is shifted elsewhere.
Matt dobrodziej, vice president of marketing and business development at lattice, said: “AI applications based on vision, sound and other sensors will revolutionize the client computing experience. Our sensai supports various network edge AI solutions, giving client devices context awareness and letting them know when, where and how they are used. Our nexus FPGA achieves this function with industry-leading low power consumption.”
Compared with the devices that use CPU to drive AI applications, the battery life of AI computing devices developed with sensai and running on lattice FPGA is prolonged by 28%. Sensai also supports on-site software update, so as to maintain the evolution of AI algorithm, and allow OEM manufacturers to flexibly select different sensors and SOC technologies to adapt their equipment.
Lattice is working with leading AI ecosystem partners to develop a roadmap for the development of lattice client computing AI experience.
Stephen Morgan Stein, vice president of mirametrix, said: “Our grace by miramatrix attention sensing software can capture the user’s face, eyes and gaze movements, so as to understand the user’s consciousness and attention. The intelligent devices developed by this unique technology can provide a more natural and immersive user experience and device interaction. Lattice’s sensai solution collection and low-power FPGA can help developers realize novel AI functions Can improve the battery life of the equipment. “
The latest version of sensai solution set (v4.1) has been released to support lattice’s AI based application roadmap. Its enhanced features and new features include:
·Client computing AI experience reference design
- User detection: when the user approaches or leaves the device, the client device will be automatically started or closed
- Attention tracking: when the user’s attention is not on the screen, reduce the screen brightness of the device, save power and prolong the service time
- Facial viewfinder: enhance video experience in video conferencing applications
- Bystander detection: detect potential peepers standing behind the device and blur the screen to ensure data privacy
·More application support – the improvement in performance and accuracy of sensai version 4.1 helps to expand its target applications, including high-precision target detection and defect detection used in automated industrial systems. The solution set has a new hardware platform, including on-board image sensors, two I2S microphones and expansion connectors for adding more sensors, which helps the development of machine learning applications based on voice and vision.
·Easy to use tool – sensai also updates the neural network compiler and supports lattice sensai studio. It is a GUI based tool with AI model library. After configuration and training, it can be applied to various mainstream application scenarios. Sensai studio now supports automl function and can create machine learning modules according to application and dataset objectives. Some models based on mobilenet machine learning reasoning training platform are designed for the latest nexus series product – lattice certuspro ™- Nx is optimized. Sensai is also compatible with other widely used machine learning platforms, including the latest versions of Caffe, keras, tensorflow and tensorflow Lite.