APRIL 2018CIOAPPLICATIONSEUROPE.COM8Machine LearningIt is broadly accepted that 2012 was the tipping point for machine learning's transition to the mainstream. The essence of machine learning is that it is often easier to search for mechanisms that can solve problems than it is to handcraft those mechanisms.Artificial neural network models have proven to be a fruitful area to search for mechanisms that can tackle a broad range of problems, from face recognition to selecting moves in board games. Searches within this space occur on two levels:1. Searching the space of neural network topologies and their hyper-parameters (transfer function(s), learning rate(s), etc.);these are usually searched manually but Google and others are beginning to introduce methods to automate the process2. Searching the space of weights on the edges (lines) that connect the vertices (nodes) that compose the network topologySupervised LearningTo date, the majority of successes in machine learninghave been achieved using "supervised learning" as the search technique. This approach performs well when it's difficult to express a rule (or function) that maps from an input to a response but where it is easier to provide lots of examples of these mappings (e.g. from loan applications to the likelihood that the loan will be repaid, from a piece of French text to a piece of English text, from a picture to a count of the number of pedestrians in it).The supervised learning process sees this body of labeled data (input/response mappings) divided into a training set and a testing set. After using the former to train (search the space of weights for) the network, the latter, unseen data is used to confirm that the resulting solution has successfully generalized to the mapping sought.AlgorithmsThe ideas that led to the development of modern neural networks started in the 1940s and the key supervised learning algorithm ("backpropagation") required to train networks with more than two layers, was in place by the 1980s. However, Geoff Hinton (machine learning pioneer and one of the co-authors of the paper introducing backpropagation) has said, "What was wrong in the 80s is that we didn't have enough (labeled data) and we didn't have enough compute power."So, what changed in 2012? Two things:1. Data: the availability of very large labeled datasets, and one in particular, ImageNet2. Hardware: affordable parallel computationData and HardwareThe data came from ImageNet, among the first very large labeled datasets, containing millions of manually labeled images (currently over 14 million). Since 2010 this dataset had been used in the "ImageNet Large-Scale Visual Recognition Challenge" (ILSVRC), where researchers compete in a range of computer vision tasks.The hardware came from advances in graphics processing units NICK ROSS, CIO, GENIUS SPORTSUnderstanding the "Eternal AI Spring"Nick RossIn MyOPINION
< Page 7 | Page 9 >