Handwriting Meets Machine Learning

There are places in the tech space where we cease to stare in amazement about what the tech can do. Instead we whine that the tech can't do more. Take the case of handwriting recognition, whether it's what we scribble notes onto a tablet or when we scan handwritten text into a PC. We wish that it was smarter, that it recognized more characters and that the text was searchable and shareable. To be honest, I shouldn't say "we". It turns out that I have zero confidence that any machine -- even all the power of the CIA and NSA computers combined -- could accurately decipher my own handwriting. In fact, my chicken-scratch cursive is a family joke. So, I'm left using the generic "we" in this case. What you may not have noticed is the progress that handwriting recognition in our everyday technology has made. It has gained intelligence in terms of accuracy, breadth of languages, searchability, and even logic in work such as flow charts. Behind that improvement is machine learning, a concept that is evolving in how it supports not only handwriting recognition, but applications such as facial recognition and language translation. That machine learning isn't so much about writing code -- yes, you need code -- but about the actual learning process. Basically, developers forcefeed massive numbers of examples into neural network based systems, and those systems start to detect patterns. Consider a high school English class where your weekend assignment is to read the complete works of Shakespeare and his late 16th century cronies so you understand their messages by Monday morning. That's how we approach machine learning today. On Thursday of this week, we will be looking at the parallel evolution of machine learning and handwriting recognition. Gary Baum, vice president of marketing for handwriting recognition software provider MyScript joins All Analytics Radio at 2 pm EDT. MyScripts software tools allow users to take, edit, and convert handwritten text in real time, and to more intuitively create, interact with, and share content in digital form. Maybe it's ironic that we're making progress in handwriting recognition at a time when school systems are considering eliminating cursive education. However, I suspect handwriting -- whether using paper and pen or screen and stylus -- will be with us for a long time. Register now for Thursday's streaming audio interview, How Machine Learning Takes Handwriting Recognition to New Levels, and join us Thursday, August 25, at 2:00 p.m. EDT.