New research shows how brain-like computers could revolutionize blockchain and AI

Recently researchers from the Technische Universität Dresden in Germany published Leading research into a new material design for neuromorphic computing, a technology that could have revolutionary implications for both blockchain and AI.

Using a technique called reservoir computing, the team developed a pattern-recognition method that uses Magnon’s vortices to execute algorithmic tasks almost instantaneously.

Not only did they develop and test the new reservoir material, but they also demonstrated the ability of neuromorphic computing to operate on a standard CMOS chip, something that can keep upside down Both blockchain and AI.

Classic computers, such as those that power our smartphones, laptops, and most of the world’s supercomputers, use binary transistors that can be on or off (expressed as a “one” or a “zero”).

Neuromorphic computers use programmable physical artificial neurons to mimic biological brain activity. Instead of processing binary files, these systems send signals to different patterns of neurons with the added factor of timing.

This is especially important for blockchain and AI because neuromorphic computers are inherently well suited for pattern recognition and machine learning algorithms.

Binary systems use Boolean algebra to perform calculations. For this reason, classic computers pose no challenge when it comes to crunching numbers. However, these systems struggle when it comes to pattern recognition, especially when the data contains noise or is missing information.

This is why classical systems take a long time to solve complex cryptography puzzles and are completely unsuitable for situations where incomplete data stands in the way of a math-based solution.

For example, in the financial, artificial intelligence, and transportation industries, there is a never-ending flow of real-time data. Classical computers grapple with hidden problems – for example, the challenge of driverless cars has so far been difficult to narrow down to a series of “true/false” computational problems.

However, neuromorphic computers are specifically built to solve problems involving the scarcity of information. In the transportation sector, it is impossible for a classical computer to predict traffic flow because there are too many independent variables. A neuromorphic computer can continuously respond to real-time data because they do not process data points one by one.

Instead, neuromorphic computers route data through pattern configurations that somewhat resemble the human brain. Our brain flashes specific patterns related to specific neural functions, and both patterns and functions can Change after some time.

Connected: How will quantum computing affect the financial sector?

The main advantage of neuromorphic computing is that, compared to classical and quantum computers, its power level is consumption Very less. This means that neuromorphic computers can significantly reduce costs in terms of time and energy when it comes to operating a blockchain and mining new blocks on existing blockchains.

Neuromorphic computers can also significantly accelerate machine learning systems, especially those that communicate with real-world sensors (self-driving cars, robots) or that process data in real time (crypto-market analytics, transportation hubs).