Suitable for always-on voice and IoT sensor applications, the new WiFi+BLE-enabled module features a STM series MCU of ARM Cortex-M4 @ 80MHz or Nuvoton MCU of ARM Cortex-M23 @ 96MHz with 1MB of flash memory and 128KB/352KB of SRAM. With 20x20 castellated pins, the module also has a USB Type C 5V power input with serial debug port and battery-powered input options, standby power mode, as well as 3 pin SWD pins for development and debugging.
“Our new module circuit board is ideal for developing machine learning applications in battery-powered devices across all kinds of use cases,” said A Prabhakar, CEO of Eoxys Systems. “Our board is readily usable, allowing customers to quickly deploy target-specific applications by building only their carrier board with built-in WiFi+BLE5.0 connectivity, enabling data to be uploaded to the cloud in real-time.”
The XENO+ module is packaged with the Syntiant NDP120 Neural Decision Processor™ that can run multiple audio and sensor machine learning applications simultaneously with minimal power consumption. The NDP120 processor is designed to natively run multiple deep neural networks on a variety of architectures, including CNNs, RNNs and fully connected networks up to 256 layers.
“Eoxys’ new module and our NDP120 with Syntiant’s second-generation Core 2 neural network engine bring highly accurate, low-power inference to edge devices for both consumer and industrial segments,” said Mallik Moturi, CBO of Syntiant. “Whether it is for person detection in the home or listening for anomalies at industrial factories, the combined technology enables a faster go-to-market ramp, and increases processing at lower power, improving battery life and ROI.”
Click https://www.eoxys.com/Solutions/Nano_ML.html to learn more about the XENO+™ WiFi+BLE Nano ML Module.
