NEW YORK, BRONX (ORDO News) — Developers from Kaspersky Lab presented an innovative spike neural network capable of analyzing its daily decisions while “sleeping.” This is reported by Gazeta newspaper.
When a neural network makes a decision during the day, it can be instantaneous and not always optimal due to the limited time for making it. However, during sleep, the spiking neural network re-analyzes its actions, taking into account more information and time to think. This allows for deeper analysis and likely better decisions in the future.
A spiking neural network models the activity of neurons in the brain closer to biological reality, using impulses (spikes) instead of continuous activations. This biologically plausible method of simulating brain activity opens new horizons in the development of artificial intelligence.
The advantage of spiking neural networks is the efficient processing of time dependencies and events in real time. This makes them indispensable in sensor systems, robotics and other areas where it is important to take into account the temporal aspects of data.
Researchers use a variety of methods to train spike neural networks, including forward spike coding and backpropagation. This type of neural network is being actively studied in the scientific and engineering community, and its application continues to expand in various fields of artificial intelligence and machine learning.
This achievement opens up the potential for us to create more intelligent and adaptive artificial systems, taking the capabilities of artificial intelligence to the next level.
—
Online:
News agencies contributed to this report, edited and published by ORDO News editors.
Contact us: [email protected]
Our Standards, Terms of Use: Standard Terms And Conditions.
To eliminate any confusion arising from different time zones and daylight saving changes, all times displayed on our platforms are in Coordinated Universal Time (UTC).