Neuromorphic computing could lead to self-learning machines

In the last couple of years, research institutions have been working on finding new concepts of how computers can process data in the future. One of these concepts is known as neuromorphic computing. Neuromorphic computing models may sound similar to artificial neural networks but have little to do with them.

Compared to traditional artificial intelligence algorithms, which require significant amounts of data to be trained on before they can be effective, neuromorphic computing systems can learn and adapt on the fly.

With the explosive growth taking place in the machine learning sphere, researchers from Germany have devised an efficient training method for neuromorphic computers.