A deep neural network based architecture was constructed to predict amino acid side chain conformation with unprecedented accuracy. Amino acid side chain conformation prediction is essential for protein homology modeling and protein design. Current widely-adopted methods use physics-based energy functions to evaluate side chain conformation. Here, using a deep neural network architecture without physics-based assumptions, we have demonstrated that side chain conformation prediction accuracy can be improved by more than 25%, especially for aromatic residues compared with current standard methods. More strikingly, the prediction method presented here is robust enough to identify individual conformational outliers from high resolution structures in a protein data bank without providing its structural factors. We envisage that our amino acid side chain predictor could be used as a quality check step for future protein structure model validation and many other potential applications such as side chain assignment in Cryo-electron microscopy, crystallography model auto-building, protein folding and small molecule ligand docking.

Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that it generalises well to the target domain. We propose a new multi-stage RL agent, DARLA (DisentAngled Representation Learning Agent), which learns to see before learning to act. DARLA's vision is based on learning a disentangled representation of the observed environment. Once DARLA can see, it is able to acquire source policies that are robust to many domain shifts - even with no access to the target domain. DARLA significantly outperforms conventional baselines in zero-shot domain adaptation scenarios, an effect that holds across a variety of RL environments (Jaco arm, DeepMind Lab) and base RL algorithms (DQN, A3C and EC).

Many of the recent approaches to polyphonic piano note onset transcription require training a machine learning model on a large piano database. However, such approaches are limited by dataset availability; additional training data is difficult to produce, and proposed systems often perform poorly on novel recording conditions. We propose a method to quickly synthesize arbitrary quantities of training data, avoiding the need for curating large datasets. Various aspects of piano note dynamics - including nonlinearity of note signatures with velocity, different articulations, temporal clustering of onsets, and nonlinear note partial interference - are modeled to match the characteristics of real pianos. Our method also avoids the disentanglement problem, a recently noted issue affecting machine-learning based approaches. We train a feed-forward neural network with two hidden layers on our generated training data and achieve both good transcription performance on the large MAPS piano dataset and excellent generalization qualities.

Constrained Local Models (CLMs) are a well-established family of methods for facial landmark detection. However, they have recently fallen out of favor to cascaded regression-based approaches. This is in part due to the inability of existing CLM local detectors to model the very complex individual landmark appearance that is affected by expression, illumination, facial hair, makeup, and accessories. In our work, we present a novel local detector -- Convolutional Experts Network (CEN) -- that brings together the advantages of neural architectures and mixtures of experts in an end-to-end framework. We further propose a Convolutional Experts Constrained Local Model (CE-CLM) algorithm that uses CEN as local detectors. We demonstrate that our proposed CE-CLM algorithm outperforms competitive state-of-the-art baselines for facial landmark detection by a large margin on four publicly-available datasets. Our approach is especially accurate and robust on challenging profile images.

By now our future is clear: We are to be cared for, entertained, and monetized by artificial intelligence. Existing industries like healthcare and manufacturing will become much more efficient; new ones like augmented reality goggles and robot taxis will become possible. But as the tech industry busies itself with building out this brave new artificially intelligent, and profit boosting, world, it's hitting a speed bump: Computers aren't powerful and efficient enough at the specific kind of math needed. While most attention to the AI boom is understandably focused on the latest exploits of algorithms beating humans at poker or piloting juggernauts, there's a less obvious scramble going on to build a new breed of computer chip needed to power our AI future. One datapoint that shows how great that need is: software companies Google and Microsoft have become entangled in the messy task of creating their own chips.

A new research paper by Google researchers Hui Fang and Meng Zhang has outlined their attempt to teach Google's AI how to take aesthetically pleasing photos. Creatism: A deep-learning photographer capable of creating professional work are the researchers attempt to apply machine learning to the creative process. The first step was to define different aesthetic aspects of photography like composition, saturation and detail. They then analyzed 15,000 high-ranking photo thumbnails from 500px.com so the neural network could begin to understand which cropping and lighting effects were the most popular. The next step was to unleash the machine on Google Street View and let it take snapshots of scenic locations and crop and light the results accordingly.

Being able to reason through potential future events is something humans are pretty good at doing, but that kind of ability is a real challenge when it comes to training AI. Taking those reasoning skills and using them to create a plan is even more difficult, but the Google DeepMind team has begun to tackle this problem. In a recent blog post, researchers describe new approaches they've developed for introducing "imagination-based planning" to AI. Other programs have been able to work in planning abilities, but only within limited environments. AlphaGo, for example, can do this well, as the researchers note in the blog post, however, they add that "environments like Go are'perfect' - they have clearly defined rules which allow outcomes to be predicted very accurately in almost every circumstance."

Deep learning has made tremendous advances in the past year. Though managers are aware of what's been happening in the research world, we're still in the early days of putting that research into practice. While the resurgence in interest stems from applications in computer vision and speech, more companies can actually use deep learning on data they already have--including structured data, text, and times-series data. All of this interest in deep learning has led to more tools and frameworks, including some that target non-experts already using other forms of machine learning (ML). Many devices will benefit from these technologies, so expect streaming applications to be infused with intelligence.

Machine learning is going through something of a renaissance these days. It seems like there are new moves forward with this technology every day, from advances in image and sound recognition to lip reading and beating us at all the games. However, this renaissance has largely been funded by Silicon Valley. Companies are scrambling to find enough programmers capable of coding for ML and deep learning. Last year was a good year for the freedom of information, as titans of the industry Google, Microsoft, Facebook, Amazon, and even Baidu open-sourced a number of their ML frameworks.

If research and advisory firm Gartner Inc. is right in its forecast, Artificial Intelligence (AI) technologies will become pervasive in almost every new software product and service by the year 2020. The growth in AI, broadly a set of computational technologies and methodologies aimed at helping machines emulate human intelligence, is being driven primarily by sophisticated algorithms, the availability of huge data sets, greater computing power, and advances in machine learning as well as deep learning. Machine learning, a subset of AI, is broadly about teaching a computer how to spot patterns and use mountains of data to make connections without any programming to accomplish the specific task. A recommendation engine is a good example. Deep learning, an advanced machine learning technique, uses layered (hence "deep") neural networks (neural nets) that are loosely modelled on the human brain.