The Next Phase in The Deep Learning Adventure

The Next Phase in The Deep Learning Adventure

deep learning

This post is also available in: heעברית (Hebrew)

A software company that’s developed a deep learning network software that makes smart products like robots and drones more autonomous and useful recently announced a major advance in deep learning. With the company’s new software that can learn with or without the cloud, the risk of forgetting previous knowledge is eliminated.

Neurala’s neural network software uses a bio-inspired approach to mimic the way the human brain learns and analyzes its environment.

The software enables a variety of smart products, from industrial drones to consumer electronics and cameras. For example, toys can learn to identify their owners, security cameras can identify specific threats, drones can “learn” how to diagnose problems at the tops of cell towers, saving humans considerable danger and drudgery, and self-driving cars can be safer and learn to avoid obstacles.

According to the company’s press release on businesswire.com, the new approach means that for the first time a self-driving car can be personalized by each owner or dealer to a specific neighborhood; a parent can teach a toy to recognize a child, without infringing on privacy; and industrial machines can be updated in the field for specific tasks.

Neurala’s breakthrough solves the “catastrophic forgetting” problem for deep learning neural networks instantly at the computing device. New objects can be added to the deep learning AI system on the fly and without a server. Systems don’t need to be retrained from the beginning, and new information can be added without risk. Neurala accomplishes this by combining different neural network architectures in a way that was previously considered impossible.

“Our breakthrough is the enabler that automotive companies, consumer electronics companies and others have needed to make deep learning useful for their customers,” said Massimiliano Versace, CEO of Neurala. “The ability to learn on the fly means that the Neurala approach enables learning directly on the device, without all the drawbacks of cloud learning. In addition, it eliminates network latency, increases real-time performance, and ensures privacy where needed. Most importantly, it will unlock the development of a sea of cloud-less applications.” Neurala will incorporate the new capability at no additional charge into the Neurala Brains for Bots SDK (software development kit). It is expected to ship in Q3 2017.

Neurala pioneered the development of deep learning neural network software for NASA to use in planetary exploration, where processing power, battery life and communications are limited. Instead of designing deep learning neural networks for super computers, as other companies do, The Neurala Brain was designed to work where the decisions need to be made.