We’re on the cusp of deep learning for the masses. You can thank Google later — Tech News and Analysis

"Google silently did something revolutionary on Thursday. It open sourced a tool called word2vec, prepackaged deep-learning software designed to understand the relationships between words with no human guidance. Just input a textual data set and let underlying predictive models get to work learning. 'This is a really, really, really big deal,' said Jeremy Howard, president and chief scientist of data-science competition platform Kaggle.  … 'It’s going to enable whole new classes of products that have never existed before.' Think of Siri on steroids, for starters, or perhaps emulators that could mimic your writing style down to the tone ... To understand Howard’s excitement, let’s go back a few days. It was Monday and I was watching him give a presentation in Chicago about how deep learning was dominating the competition in Kaggle, the online platform where organization present vexing predictive problems and data scientists compete to create the best models. Whenever someone has used a deep learning model to tackle one of the challenges, he told the room, it has performed better than any model ever previously devised to tackle that specific problem ... But there’s a catch: deep learning is really hard. So far, only a handful of teams in hundreds of Kaggle competitions have used it. Most of them have included Geoffrey Hinton or have been associated with him.  Hinton is a University of Toronto professor who pioneered the use of deep learning for image recognition and is now a distinguished engineer at Google, as well. What got Google really interested in Hinton — at least to the point where it hired him — was his work in an image-recognition competition called ImageNet. For years the contest’s winners had been improving only incrementally on previous results, until Hinton and his team used deep learning to improve by an order of magnitude ... Deep learning, Howard explained, is essentially a bigger, badder take on the neural network models that have been around for some time. It’s particularly useful for analyzing image, audio, text, genomic and other multidimensional data that doesn’t lend itself well to traditional machine learning techniques.  Neural networks work by analyzing inputs (e.g., words or images) and recognizing the features that comprise them as well as how all those features relate to each other. With images, for example, a neural network model might recognize various formations of pixels or intensities of pixels as features.  Trained against a set of labeled data, the output of a neural network might be the classification of an input as a dog or cat, for example. In cases where there is no labeled training data — a process called self-taught learning — neural networks can be used to identify the common features of their inputs and group similar inputs even though the models can’t predict what they actually are. Like when Google researchers constructed neural networks that were able to recognize cats and human faces without having been trained to do so.  In deep learning, multiple neural networks are 'stacked' on top of each other, or layered, in order to create models that are even better at prediction because each new layer learns from the ones before it. In Hinton’s approach, each layer randomly omits features — a process called “dropout” — to minimize the chances the model will overfit itself to just the data upon which it was trained. That’s a technical way of saying the model won’t work as well when trying to analyze new data ... Which brings us back to word2vec. Google calls it 'an efficient implementation of the continuous bag-of-words and skip-gram architectures for computing vector representations of words.' Those 'architectures' are two new natural-language processing techniques developed by Google researchers Tomas Mikolov, Ilya Sutskever, and Quoc Le (Google Fellow Jeff Dean was also involved, although modestly, he told me.) They’re like neural networks, only simpler so they can be trained on larger data