MPAI after MPEG

MPAI after MPEG

Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI) is born with the mission of taking advantage of Artificial Intelligence to define data coding standards. The NeuroMem neurons are perfect candidates to develop these standards with use models including non supervised annotation, novelty detection and classification without duplication, data modeling and compression.

The MPAI community is no less than the successor of MPEG and founded by the same Leonardo Chiariglione. Guy Paillet, president of General Vision, is honored to have been invited by Mr.  Chiariglione to join MPAI as a board member and Vice President.

MPAI Community

Stay tune to hear more about the process of the community.

Smallest smart sensor hub with real-time learning

Smallest smart sensor hub with real-time learning

NeuroTile is a complete IOT solution to monitor motion, temperature and audio signals, relying on a single or multiple NeuroMem neural networks for the learning,  classification and anomaly detection, and using an STM32 microcontroller for the selective storage of data or its transmission over low-power BLE.

General Vision is expanding the NeuroTile library to support additional external sensors including a camera, thus turning it into the ideal platform for Neurotile is a comprehensive IOT platform for the condition monitoring of humans and machines, as well as smart instrumentation and prediction.

Towards cognitive storage

Towards cognitive storage

General Vision is an advocate of in-storage analytics which will bring more security and lower power consumption by  eliminating the need to transfer datasets back and forth between their location of storage and servers doing cloud analytics. We believe that NeuroMem chips are enablers for the integration of analytics inside solid state storage and are pleased to announce that our patent labeled “Cognitive Storage Device” is not published and pending issuance.

Neurons help pit and stuff olives with accuracy

Neurons help pit and stuff olives with accuracy

Once again the NeuroMem neurons help solve an industrial application with simplicity and accuracy. This time they are trained to recognize the acceptable aspect of olives and their proper alignment in a pocket to be pitted and stuffed, thus improving the quality of the goods and reducing waste. This collaborative study involves four major universities in Spain and is published in the Special Issue “IoT Technologies and the Agricultural Value Chain” of the Sensors journal.

Download the paper.

Note that the CM1K chip mentioned in the paper has reached its end of life, but its successor, the NM500, is composed of the same neurons and controlled with the library of registers. A  firmware version of the neurons is also available for FPGA.