Kaspersky Lab developers created a spiking neural network with a sleep function. Andrey Lavrentyev, head of Kaspersky Lab’s technology development department, told socialbites.ca that during sleep the neural network once again analyzes daytime decisions.
“The day passed, a lot of information came, the system digested it. The neural network makes a decision that needs to be made immediately, not within an hour. This solution may not be the optimal solution. And this experience accumulated in one day. But if we had taken more time and gone back to consider, analyze and compare more information, perhaps our decision would have been different. Our neural network comes into play after the analysis, makes more conscious decisions in the dream and learns from them,” explained Lavrentiev.
According to him, spike networks work with events; Memory, attention and artificial intelligence elements of the future can be built on these.
“I believe that the development of architectures for spike networks opens up tremendous opportunities, including self-learning networks,” the expert said.
Learn more about what artificial intelligence will look like in the future, what neuromorphic chips are and how they work. report Lavrentyev “socialbites.ca”.
Previously at Sechenov Moscow State Medical University was created A neural network that predicts the risk of stroke in the eye vessels.