Derby scientists help make international artificial intelligence breakthrough

A team of data science professors have developed a revolutionary system that accelerates artificial intelligence algorithms, enabling supercomputers to master artificial neural networks (ANN) as complex as the human brain.

The proposed method, called Sparse Evolutionary Training, also gives full artificial intelligence capability to inexpensive computers, meaning it will be possible to turn any internet device into an intelligent Internet of Things object which can send and receive data. 

Artificial neural networks are widely used in industry, science and medicine to make sense of vast amounts of data, such as in medical diagnostics and personalised medicine. But ANNs are typically made up of lots of layers and millions of nodes, which means their intelligence is severely limited and requires super-computational power.

The team of scientists from the University of Derby, Eindhoven University of Technology in the Netherlands, and the University of Texas, Austin, have joined together to develop a method that could push artificial intelligence well beyond its current boundaries. The new system substantially accelerates machine learning by replacing the typical neuronal networks with sparse layers, enabling the use of artificial intelligence in major problems such as genetic disease diagnostics. 

Antonio Liotta, Professor of Data Science and Director of the Data Science Research Centre at the University of Derby, said: “Artificial neural networks are at the very heart of the artificial intelligence revolution that is shaping every aspect of society and technology. They have led to major breakthroughs in various domains including speech recognition and computer vision.

“However, the networks we have been able to handle so far are nowhere near the capacity of the human brain – made up of billions of neurons.

“The very latest supercomputers would struggle with a 16 million neuron network the size of a frog’s brain, while it would take more than a dozen days for a powerful desktop computer to process a mere 100,000 neuron network.

“We have benchmarked our approach on 15 datasets from different problem domains including genetics, biology, natural language processing, imaging and particle physics.

“This work represents a major breakthrough in fundamental artificial intelligence and has immediate practical implications in industry and academia alike, enabling the analysis of vast sets of data, beyond what is currently possible.”

The full research paper has been published in Nature Communications, and can be found here.