By: Favour Nerrise
According to Forbes magazine, “While ML [Machine Learning] is often described as a sub-discipline of AI, it’s better to think of it as the current state-of-the-art – it’s the field of AI which today is showing the most promise at providing tools that industry and society can use to drive change. In turn, it’s probably most helpful to think of Deep Learning as the cutting-edge of the cutting-edge.”
Deep learning (DL) is a kind of representation learning, which is in turn, a kind of machine learning used for many but not all approaches to AI. DL has been successfully used in some commercial applications since the 1990s but was often regarded as being more of an art than technology and something that only an expert could use, until recently. The age of “Big Data” has made deep learning much easier because the key burden of statistical estimation – generalizing well to new data after observing only a small amount of data – has been considerably lightened.
DL has also consistently been applied with success to broader and broader sets of applications. The earliest deep models were used to recognize individual objects in tightly cropped, extremely small images. Since then there has been a gradual increase in the size of images neural networks could process. Modern object recognition networks process rich high-resolution photographs and do not have a requirement that the photo is cropped near the object to be recognized. Deep learning has also had a dramatic impact on speech recognition, pedestrian detection, and image segmentation.
Many of these applications of deep learning are highly profitable. Deep learning is now used by many top technology companies, including Google, Microsoft, Facebook, IBM, Baidu, Apple, Adobe, Netflix, NVIDIA, and NEC.
Deep learning has also made contributions to other sciences. Modern convolutional networks for object recognition provide a model of visual processing that neuroscientists can study. Deep learning also provides useful tools for processing massive amounts of data and making useful predictions in scientific fields
In summary, deep learning is an approach to machine learning that has drawn heavily on our knowledge of the human brain, statistics, and applied math as it developed over the past several decades. One of its primary applications is medical diagnostics involving predictive analysis of EEG data, MRIs, and treatment decisions of brain disorders.