Unlike similar touch pads on hand-held computers or on laptops, which only recognize input from a single point, this surface can process information from multiple points, allowing for more rapid typing.
The company has said that it uses deep learning, a popular machine-learning technique based on training a many-layered network of simulated neurons to recognize input using a large number of training examples.
The HNN is known to be able to recognize input patterns from a set of stored patterns [15, 21].
Taking loose inspiration from neuroscience, an RCN is encoded with assumptions about visual information like edges or curves which it then uses to recognize inputs it hasn't encountered in training.
They are trained to recognize inputs (e.g. peptide sequences) associated with a given output (e.g. binding affinity).
Basically you've got some sort of tablet app for recognizing pen input in phrases instead of in "chunks".
It's also better at recognizing voice input and gestures, and it can even read your heartbeat while you're excercising.
It turns out that Dragon ID is quite the polyglot too, as the service is capable of recognizing voice input in English, French, German, Italian, Spanish, Chinese, Japanese and Korean.
The interface learns at runtime; if the interface fails in correctly recognizing an input instance of a gesture, the user specifies the correct label of the instance and the interface includes it to the corresponding AT.
Name My Tune: http://www.namemytune.com/ (users recognizing song input of other users).
That is, the proposal is an exemplar-based model that "recognizes input and generates outputs by analogical evaluation across a lexicon of distinct memory traces of remembered tokens of speech" (Gahl & Yu, 2006: 213; see also Bod, 2009).
