In the past 10 years, the best-performing artificial-intelligence systems--such as the speech recognizers on smartphones or Google's latest automatic translator--have resulted from a technique called "deep learning." Deep learning is in fact a new name for an approach to artificial intelligence called neural networks, which have been going in and out of fashion for more than 70 years. Neural networks were first proposed in 1944 by Warren McCullough and Walter Pitts, two University of Chicago researchers who moved to MIT in 1952 as founding members of what's sometimes called the first cognitive science department. Neural nets were a major area of research in both neuroscience and computer science until 1969, when, according to computer science lore, they were killed off by the MIT mathematicians Marvin Minsky and Seymour Papert, who a year later would become co-directors of the new MIT Artificial Intelligence Laboratory. The technique then enjoyed a resurgence in the 1980s, fell into eclipse again in the first decade of the new century, and has returned like gangbusters in the second, fueled largely by the increased processing power of graphics chips.

In emotion recognition, it is difficult to recognize human's emotional states using just a single modality. Besides, the annotation of physiological emotional data is particularly expensive. These two aspects make the building of effective emotion recognition model challenging. In this paper, we first build a multi-view deep generative model to simulate the generative process of multi-modality emotional data. By imposing a mixture of Gaussians assumption on the posterior approximation of the latent variables, our model can learn the shared deep representation from multiple modalities. To solve the labeled-data-scarcity problem, we further extend our multi-view model to semi-supervised learning scenario by casting the semi-supervised classification problem as a specialized missing data imputation task. Our semi-supervised multi-view deep generative framework can leverage both labeled and unlabeled data from multiple modalities, where the weight factor for each modality can be learned automatically. Compared with previous emotion recognition methods, our method is more robust and flexible. The experiments conducted on two real multi-modal emotion datasets have demonstrated the superiority of our framework over a number of competitors.

Our goal is to learn a semantic parser that maps natural language utterances into executable programs when only indirect supervision is available: examples are labeled with the correct execution result, but not the program itself. Consequently, we must search the space of programs for those that output the correct result, while not being misled by spurious programs: incorrect programs that coincidentally output the correct result. We connect two common learning paradigms, reinforcement learning (RL) and maximum marginal likelihood (MML), and then present a new learning algorithm that combines the strengths of both. The new algorithm guards against spurious programs by combining the systematic search traditionally employed in MML with the randomized exploration of RL, and by updating parameters such that probability is spread more evenly across consistent programs. We apply our learning algorithm to a new neural semantic parser and show significant gains over existing state-of-the-art results on a recent context-dependent semantic parsing task.

Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The outputs are represented as abstract syntax trees (ASTs) and constructed by a decoder with a dynamically-determined modular structure paralleling the structure of the output tree. On the benchmark Hearthstone dataset for code generation, our model obtains 79.2 BLEU and 22.7% exact match accuracy, compared to previous state-of-the-art values of 67.1 and 6.1%. Furthermore, we perform competitively on the Atis, Jobs, and Geo semantic parsing datasets with no task-specific engineering.

Deep Learning gets more and more traction. It basically focuses on one section of Machine Learning: Artificial Neural Networks. This article explains why Deep Learning is a game changer in analytics, when to use it, and how Visual Analytics allows business analysts to leverage the analytic models built by a (citizen) data scientist. Deep Learning is the modern buzzword for artificial neural networks, one of many concepts and algorithms in machine learning to build analytics models. A neural network works similar to what we know from a human brain: You get non-linear interactions as input and transfer them to output. A neural network is a supervised algorithm in most cases, which uses historical data sets to learn correlations to predict outputs of future events, e.g. for cross selling or fraud detection.

And we'd like to help. Since we've already done a crapload of research (and gotten a lot of customer and expert feedback) on which AI events are likely to be the must-attends of the next year, we thought we'd do you a solid and let you know which conferences we're headed to in the coming months. We've also listed other top contenders we won't make it to but may interest you. Hope to see you at a show or two next year! Explore how deep learning will impact healthcare, manufacturing, search & transportation." Where do the challenges still lie in research and application? We're exploring the convergence of software & hardware to create safer, smarter and more efficient transport."

We are on the edge of a new reality, powered and enabled by artificial intelligence. In the next decade, we could see all aspects of our society transformed. Those to change first will be data-rich industries like healthcare, financial services and energy. Canada's new AI lab, The Vector Institute – of which I sit on the board of directors – has a focus in Deep Learning, pioneered by Geoff Hinton, with applications in a wide variety of fields including healthcare, financial services, manufacturing and material science. And that means breakthroughs in healthcare are coming--and it goes far beyond image classification.

A supercomputer whirs away in London, crunching complex drug chemistries into deep learning algorithms to discover new medications. A few miles away, a DeepMind neural network scans millions of images from Moorfields Eye Hospital, searching for signs of eye disease. The application casually asks if you still have that headache from yesterday and if you'd like to book a doctor's appointment for tomorrow. Of all the fields that artificial intelligence will disrupt in the coming years, healthcare may see the greatest paradigm shift. AI's influence in the industry will be deep and broad.

Yann LeCun once built an AI chip called ANNA. But he was 25 years ahead of his time. The year was 1992, and LeCun was a researcher at Bell Labs, the iconic R&D lab outside New York City. He and several other researchers designed this chip to run deep neural networks--complex mathematical systems that can learn tasks on their own by analyzing vast amounts of data--but ANNA never reached the mass market. Neural networks were pretty good at recognizing letters and numbers scrawled onto personal checks and envelopes, but they didn't work all that well when performing other tasks, at least not in any practical sense. Today, however, neural networks are rapidly transforming the internet's biggest players, including Google, Facebook, and Microsoft.

An AI has learned to tackle one of the toughest Atari videogames by taking instructions in plain English. The system, developed by a team at Stanford University in California, learned to play the game Montezuma's Revenge, in which players scour an Aztec temple for treasure. The game is challenging for AI to learn because it offers sparse rewards, requiring players to make several moves before earning any points. Most videogame-playing AIs use reinforcement learning to develop a strategy, relying on feedback like game points to tell them when they are playing well. To help their AI pick up game tactics quicker, the Stanford team gave their reinforcement learning system a helping hand in the form of natural language instructions, for example advising it to "climb up the ladder" or "get the key".