Facebook's deep-learning artificial intelligence systems have learned to recognize your friends in your photos, and Google's AI has learned to anticipate what you'll be searching for. But there's no need to feel left out, even if your company's computers haven't learned much lately. A growing number of tech giants and startups have begun offering machine learning as a cloud service. That means other companies and startups do not need to develop their own specialized hardware or software to apply deep learning--the high-powered version du jour of machine learning--to their specific business needs. "Deep-learning algorithms dominate other machine-learning methods when data sets are large," says Zachary Chase Lipton, a deep-learning researcher in the Artificial Intelligence Group at the University of California, San Diego, who has examined cloud AI services from companies such as Amazon and IBM.

Artificial intelligence is taking the automobile industry by storm while all the major automobile players are utilizing their resources and technology to come up with the best. The beauty of devices with artificial intelligence is that it tries to learn from sensory inputs like real sounds and images. In the same way, when intelligence is applied to the technology within an automobile, it would recognize the environment and evaluate the contextual implications when it moves or faces any hurdles. In 2015, the install rate of AI based systems in new vehicles was just 8%; this number is expected to soar to 109% in 2025. This is because different kinds of AI systems will be installed in vehicles.

Canadian researchers have been behind some recent major breakthroughs in artificial intelligence. Now, the country is betting on becoming a big player in one of the hottest fields in technology, with help from the likes of Google and RBC. In an unassuming building on the University of Toronto's downtown campus, Geoff Hinton laboured for years on the "lunatic fringe" of academia and artificial intelligence, pursuing research in an area of AI called neural networks. Also known as "deep learning", neural networks are computer programs that learn in similar way to human brains. The field showed early promise in the 1980s, but the tech sector turned its attention to other AI methods after that promise seemed slow to develop.

This paper proposes to improve visual question answering (VQA) with structured representations of both scene contents and questions. A key challenge in VQA is to require joint reasoning over the visual and text domains. The predominant CNN/LSTM-based approach to VQA is limited by monolithic vector representations that largely ignore structure in the scene and in the form of the question. CNN feature vectors cannot effectively capture situations as simple as multiple object instances, and LSTMs process questions as series of words, which does not reflect the true complexity of language structure. We instead propose to build graphs over the scene objects and over the question words, and we describe a deep neural network that exploits the structure in these representations. This shows significant benefit over the sequential processing of LSTMs. The overall efficacy of our approach is demonstrated by significant improvements over the state-of-the-art, from 71.2% to 74.4% in accuracy on the "abstract scenes" multiple-choice benchmark, and from 34.7% to 39.1% in accuracy over pairs of "balanced" scenes, i.e. images with fine-grained differences and opposite yes/no answers to a same question.

The ability to predict how an environment changes based on forces applied to it is fundamental for a robot to achieve specific goals. For instance, in order to arrange objects on a table into a desired configuration, a robot has to be able to reason about where and how to push individual objects, which requires some understanding of physical quantities such as object boundaries, mass, surface friction, and their relationship to forces. A standard approach in robot control is to use a physical model of the environment and perform optimal control to find a policy that leads to the goal state. For instance, extensive work utilizing the MuJoCo physics engine [1] has shown how strong physics models can enable solutions to control problems in complex and contact-rich environments [2]. A shortcoming of such models is, however, that they rely on very accurate estimates of the state of the system [3].

Artificial neural networks (ANNs) have gained a well-deserved popularity among machine learning tools upon their recent successful applications in image- and sound processing and classification problems. ANNs have also been applied for predicting the family or function of a protein, knowing its residue sequence. Here we present two new ANNs with multi-label classification ability, showing impressive accuracy when classifying protein sequences into 698 UniProt families (AUC=99.99%) and 983 Gene Ontology classes (AUC=99.45%).

Empirical scoring functions based on either molecular force fields or cheminformatics descriptors are widely used, in conjunction with molecular docking, during the early stages of drug discovery to predict potency and binding affinity of a drug-like molecule to a given target. These models require expert-level knowledge of physical chemistry and biology to be encoded as hand-tuned parameters or features rather than allowing the underlying model to select features in a data-driven procedure. Here, we develop a general 3-dimensional spatial convolution operation for learning atomic-level chemical interactions directly from atomic coordinates and demonstrate its application to structure-based bioactivity prediction. The atomic convolutional neural network is trained to predict the experimentally determined binding affinity of a protein-ligand complex by direct calculation of the energy associated with the complex, protein, and ligand given the crystal structure of the binding pose. Non-covalent interactions present in the complex that are absent in the protein-ligand substructures are identified and the model learns the interaction strength associated with these features. We test our model by predicting the binding free energy of a subset of protein-ligand complexes found in the PDBBind dataset and compare with state-of-the-art cheminformatics and machine learning-based approaches. We find that all methods achieve experimental accuracy (less than 1 kcal/mol mean absolute error) and that atomic convolutional networks either outperform or perform competitively with the cheminformatics based methods. Unlike all previous protein-ligand prediction systems, atomic convolutional networks are end-to-end and fully-differentiable. They represent a new data-driven, physics-based deep learning model paradigm that offers a strong foundation for future improvements in structure-based bioactivity prediction.

In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove that any rectifier net of any depth can be represented by a maximum of a number of functions that can be realized by a shallow network with a single hidden layer. The transformations of both deep rectifier nets and deep residual nets are conducted to demonstrate the advantages of the residual nets over the conventional neural nets and the advantages of the deep neural nets over the shallow neural nets. In summary, for two rectifier nets with different depths but with same total number of hidden units, the corresponding single hidden layer representation of the deeper net is much more complex than the corresponding single hidden representation of the shallower net. Similarly, for a residual net and a conventional rectifier net with the same structure except for the skip connections in the residual net, the corresponding single hidden layer representation of the residual net is much more complex than the corresponding single hidden layer representation of the conventional net.

Natural Language Processing (or NLP) is an area that is a confluence of Artificial Intelligence and linguistics. It involves intelligent analysis of written language. If you have a lot of data written in plain text and you want to automatically get some insights from it, you need to use NLP techniques. These insights could be -- sentiment analysis, information extraction, information retrieval, search etc. to name a few. Machine Learning (or ML) is an area of Artificial Intelligence (AI) that is a set of statistical techniques for problem solving.

I love to write about face recognition, image recognition and all the other cool things you can build with machine learning. Whenever possible, I try to include code examples or even write libraries/APIs to make it as easy as possible for a developer to play around with these fun technologies. But the number one question I get asked is "How in the world do I get all these open source libraries installed and working on my computer?" If you aren't a long-time Linux user, it can be really hard to figure out how to get a system fully configured with all the required machine learning libraries and tools like TensorFlow, Theano, Keras, OpenCV, and dlib. The majority of the issues that get filed on my own open source projects are about how to install these tools.