In embedded applications that use neural networks (NNs) for classification tasks, it is important to not only minimize the power consumption of the NN calculation, but of the whole system.

Low-power applications represent a significant portion of the future market for embedded systems. Every year, more designers are required to make designs portable, wireless and energy efficient. This ...

The annual show for the embedded electronics supply chain showcased many innovations in edge AI and connected, intelligent ...

Codasip debuted two new customizable low power embedded RISC-V processor cores. To support embedded AI applications, the L31/L11 cores run Google’s TensorFlowLite for Microcontrollers. Codasip Studio ...

New Accelerated Processing Unit (APU) ideal for industrial control, point-of-sale, medical appliance and transportation markets. Said to deliver three times the performance, reduce power consumption ...

A new study presents a system-level design framework for a low-power embedded sensor node capable of performing machine learning inference directly on-site. Study: Low-Power Embedded Sensor Node for ...

The approach would enable systems of low-power embedded devices to be connected and managed seamlessly under the IP umbrella regardless of the type of physical links on which they are connected. A new ...

Timing devices supply the heartbeat for compact, wirelessly connected IoT devices that can sense, process, and communicate seamlessly with cloud and mobile platforms. These requirements place strict ...

Raspberry Pi has introduced and released the new Raspberry Pi Compute Module 5. I happen to have four Raspberry Pi Compute Module 5 devices on my bench along with a couple of Raspberry Pi Compute ...