NXP extends the embedded AI environment to edge processing applications. NXP's machine learning solution supports scalable processing solutions while taking into account cost and end-user experience requirements.
NXP Semiconductors has announced the introduction of an easy-to-use, generalized machine learning development environment for building innovative applications with high-end features. Customers can now easily implement machine learning capabilities for NXP devices ranging from low-cost microcontrollers (MCUs) to breakthrough cross-border i.MX RT processors and high-performance application processors.
The machine learning development environment provides a complete set of ready-to-use solutions. Users can select the best execution engine from ARM Cortex cores to high-performance GPU/DSP (graphics processing unit/digital signal processor) complexes, and also provide deployment on these engines. Machine learning model (including neural network) tools.
Emerging Embedded AI
Embedded artificial intelligence (AI) is rapidly becoming the basic technological capability of edge processing, enabling “smart” devices to “recognize” the surrounding environment and make decisions based on the information received with little or no human intervention. NXP's machine learning development environment helps the rapid growth of machine learning in visual, speech and anomaly detection applications.
Vision-based machine learning applications provide input information through cameras to various types of machine learning algorithms, where neural networks are the most popular. These applications cover most of the subdivided vertical markets and can perform functions such as object recognition, authentication, and staff statistics. Voice activation devices (VADs) are driving the need for edge machine learning to enable wake-up word detection, natural language processing, and “voice user interface” applications. Machine learning-based anomaly detection (according to the vibration/sound mode) can identify impending failures, thereby significantly reducing equipment downtime and enabling rapid changes in Industry 4.0. NXP offers its customers multiple solutions for integrating machine learning into their applications.
Machine learning goes to the edge
NXP's machine learning development environment provides free software that allows customers to import their own trained TensorFlow or Caffe models, convert them to an optimized AI inference engine, and deploy NXP's extensive scalable processing solutions from MCU to highly integrated i.MX and Layerscape processors).
"When using machine learning in embedded applications, it is necessary to balance both cost and end-user experience. For example, AI inference engines can be deployed in our cost-effective MCUs, and get enough performance, which many people are still surprised. "Markus Levy, head of NX's artificial intelligence technology, said: "On the other hand, our high-performance cross-border and application processors also have powerful processing capabilities, enabling rapid AI reasoning and training in many customer applications. With AI applications As we continue to expand, we will continue to drive growth in this application area with next-generation processors designed to accelerate machine learning."
Another key requirement for the introduction of AI/machine learning technology into edge computing applications is the ease and security of deploying and upgrading embedded devices from the cloud. The EdgeScale platform supports secure configuration and management of IoT and edge devices. EdgeScale achieves an end-to-end continuous development and delivery experience by integrating AI/machine learning and inference engines in the cloud and automatically deploying integrated modules to edge devices.
In order to meet a wide range of customer needs, NXP has also created a machine learning partner ecosystem that connects customers with technology suppliers to accelerate product development through proven machine learning tools, inference engines, solutions and design services. Production and time to market. Members of the ecosystem include Au-Zone Technologies and Pilot.AI.
Au-Zone Technologies Delivers Industry's First End-to-End Embedded Machine Learning Toolkit and Operational Reasoning Engine DeepView to Enable Developers to Compete with All of NXP's SoC Portfolios (including Arm Cortex-A, Cortex-M Core, and GPU) Configure and set CNN on the hybrid.
Pilot.AI has built a framework to implement various sensing tasks on various customer platforms (from microcontrollers to GPUs), including detection, classification, tracking and identification, and provides data collection/classification tools and pre-trained Models to directly implement model deployment.