Promise of deep-learning programmes

Written by New York Times | Updated: Nov 25 2012, 06:35am hrs
Advances in an artificial intelligence technology that can recognise patterns offer the possibility of machines that perform human activities like seeing, listening and thinking

John Markoff

Using an artificial intelligence technique inspired by theories about how the brain recognises patterns, technology companies are reporting startling gains in fields as diverse as computer vision, speech recognition and the identification of promising new molecules for designing drugs. The advances have led to widespread enthusiasm among researchers who design software to perform human activities like seeing, listening and thinking. They offer the promise of machines that converse with humans and perform tasks like driving cars and working in factories, raising the specter of automated robots that could replace human workers.

The technology, called deep learning, has already been put to use in services like Apples Siri virtual personal assistant, which is based on Nuance Communications speech recognition service, and in Googles Street View, which uses machine vision to identify specific addresses. But what is new in recent months is the growing speed and accuracy of deep-learning programmes, often called artificial neural networks or just neural nets for their resemblance to the neural connections in the brain.

There has been a number of stunning new results with deep-learning methods, said Yann LeCun, a computer scientist at New York University who did pioneering research in handwriting recognition at Bell Laboratories. The kind of jump we are seeing in the accuracy of these systems is very rare indeed. Artificial intelligence researchers are acutely aware of the dangers of being overly optimistic. Their field has long been plagued by outbursts of misplaced enthusiasm followed by equally striking declines. In the 1960s, some computer scientists believed that a workable artificial intelligence system was just 10 years away. In the 1980s, a wave of commercial start-ups collapsed, leading to what some people called the AI winter.

But recent achievements have impressed a wide spectrum of computer experts. In October, for example, a team of graduate students studying with the University of Toronto computer scientist Geoffrey E Hinton won the top prize in a contest sponsored by Merck to design software to help find molecules that might lead to new drugs. From a data set describing the chemical structure of 15 different molecules, they used deep-learning software to determine which molecule was most likely to be an effective drug agent. The achievement was particularly impressive because the team decided to enter the contest at the last minute and designed its software with no specific knowledge about how the molecules bind to their targets. The students were also working with a relatively small set of data; neural nets typically perform well only with very large ones.

This is a really breathtaking result because it is the first time that deep learning won, and more significantly it won on a data set that it wouldnt have been expected to win at, said Anthony Goldbloom, chief executive and founder of Kaggle, a company that organises data science competitions, including the Merck contest. Advances in pattern recognition hold implications not just for drug development but for an array of applications, including marketing and law enforcement. With greater accuracy, for example, marketers can comb large databases of consumer behaviour to get more precise information on buying habits. And improvements in facial recognition are likely to make surveillance technology cheaper and more commonplace.

Artificial neural networks, an idea going back to the 1950s, seek to mimic the way the brain absorbs information and learns from it. In recent decades, Dr Hinton, 64 (a great-great-grandson of the 19th-century mathematician George Boole, whose work in logic is the foundation for modern digital computers), has pioneered powerful new techniques for helping the artificial networks recognise patterns. Modern artificial neural networks are composed of an array of software components, divided into inputs, hidden layers and outputs. The arrays can be trained by repeated exposures to recognise patterns like images or sounds.

These techniques, aided by the growing speed and power of modern computers, have led to rapid improvements in speech recognition, drug discovery and computer vision. Deep-learning systems have recently outperformed humans in certain limited recognition tests. Last year, for example, a programme created by scientists at the Swiss AI Lab at the University of Lugano won a pattern recognition contest by outperforming both competing software systems and a human expert in identifying images in a database of German traffic signs. The winning programme accurately identified 99.46% of the images in a set of 50,000; the top score in a group of 32 human participants was 99.22%, and the average for the humans was 98.84%.

Deep learning was given a particularly audacious display at a conference last month in Tianjin, China, when Richard F Rashid, Microsofts top scientist, gave a lecture in a cavernous auditorium while a computer programme recognised his words and simultaneously displayed them in English on a large screen above his head. Then, in a demonstration that led to stunned applause, he paused after each sentence and the words were translated into Mandarin Chinese characters, accompanied by a simulation of his own voice in that language, which Rashid has never spoken. The feat was made possible, in part, by deep-learning techniques that have spurred improvements in the accuracy of speech recognition. Rashid, who oversees Microsofts worldwide research organisation, acknowledged that while his companys new speech recognition software made 30% fewer errors than previous models, it was still far from perfect.

Rather than having one word in four or five incorrect, now the error rate is one word in seven or eight, he wrote on Microsofts web site. Still, he added that this was the most dramatic change in accuracy since 1979, and as we add more data to the training we believe that we will get even better results. One of the most striking aspects of the research led by Dr Hinton is that it has taken place largely without the patent restrictions and bitter infighting over intellectual property that characterise high-technology fields. We decided early on not to make money out of this, but just to sort of spread it to infect everybody, he said. These companies are terribly pleased with this.