Machine learning (ML), a subfield of artificial intelligence, teaches computers to solve tasks based on structured data, language, audio, or images, by providing examples of inputs and the desired outputs. This is different from traditional computer programming, where programmers write a sequence of specific instructions. Here, the ML model learns to generate desirable outputs by adjusting its many knobs – often in the millions.
ML has a history of developing methods with hand-crafted features that may work only for specific, narrow problems. There are several such examples. In text, classifying a document as scientific or literary may be solved by counting the number of times certain words appear. In audio, spoken text is recognised by converting the audio into a time-frequency representation. In images, a car may be found by checking for the existence of specific car-like edge-shaped patterns.
Such hand-crafted features are combined with simple, or shallow, learning classifiers that typically have up to tens of thousands of knobs. In technical parlance, these knobs are called parameters.
