Artificial intelligence startup Neurala Inc. is claiming a major breakthrough with its deep learning platform, saying it has reduced the time it takes to train a deep neural network from 15 hours to just 20 seconds.

Neurala claims to differentiate itself from other AI software makers because its platform learns by mimicking the human brain, integrating sight, sound and other senses into one system in a rough emulation of how the mind works. The startup added that its deep learning software further excels because it doesn’t rely on servers running in the cloud to train its systems, therefore making it suitable for a new generation of smart cars, children’s toys and industrial machines that perform computations at the edge of the network.

Now, the company said, its Lifelong Deep Neural Network technology is better than ever, slashing learning times to mere seconds and also providing the ability for neural networks to acquire new knowledge without forgetting the previous information it learned – something it claims wasn’t possible before.

“It takes a very long time to train a traditional DNN on a dataset, and once that happens, it must be completely retrained if even a single piece of new information is added,” said Anatoli Gorchetchnikov, Neurala’s chief technology officer.

Traditional deep neural networks have always been “fixed,” Neurala said, which means that once the training was complete, there can be no additional training to improve the model without relearning the knowledge it already possessed.

“[Traditional] deep neural networks still rely on a learning algorithm developed in the ’80s called backpropagation,” Neurala Chief Executive Officer Massimiliano Versace told SiliconANGLE. “This algorithm works but requires many iterations over the dataset, making it really slow, and all the data for future expansion of system knowledge must be kept.”

However, Neurala’s Lifelong DNN works differently, learning about objects it sees incrementally in a way that mimics the cortical and subcortical circuits of the human brain, thereby allowing it to add new information on the fly. The company said its latest breakthrough was made possible thanks to ImageNet, a massive database of images organized by keywords, and other more specific datasets.

The company also said there’s no negative impact on the inference times, memory or precision of its deep neural networks. In addition, the new Lifelong-DNN can complete its training using just 20 percent of the number of instances used by earlier iterations of its software.

“What we did is we designed a new class of neural networks that retain the power of DNN, without requiring long training times and the need to keep all training data to add new knowledge,” Versace said. “We achieved this as a result of looking more closely at cortical and subcortical anatomy and physiology and coming out with algorithms that more closely mimic the way humans learn day after day.”

Gorchetchnikov called the update “game-changing for edge analytics and for the way servers are used today. We can envision this technology slashing compute powers in server farms and enabling networks to be assembled on the fly on custom data. We are only scratching the surface of potential applications.”

Neurala’s technology already fulfills a number of applications. For example, it helps security cameras learn about and identify specific threats. Drones using the technology can learn how to diagnose problems at cell towers they’re inspecting, eliminating the need for a human to climb to the top and inspect it.

The company is also dead set on using its technology for the greater good. Last year, for example, it said it was teaming up with Motorola Solutions Inc. to build “intelligent cameras” that can be worn by police officers to help search for missing children and other persons or objects of interest. Also in 2017, Neurala said it was working with the Lindbergh Foundation to combat illegal poaching in Africa by kitting out drones with AI software that can identify poachers and direct authorities to their location to intercept them.

Image: Neurala