Typically, the development of GPU kernels is a laborious process. However, if the algorithms can be expressed using combinations of high-level operators then it should be possible to generate the GPU kernel. This is what CCT is designed to do. An offshoot of CCT is the Operator Vectorization Library (OVL). OVL is a python library that does the same a CCT but for TensorFlow framework.

U.S. technology multinational IBM announced today it will open a laboratory in Montreal to strengthen its collaboration with the Montreal Institute for Learning Algorithms (MILA), led by Professor Yoshua Bengio. MILA is the world's largest research group in the field of artificial intelligence and deep learning. It is based at Université de Montréal and brings together about 100 researchers. The new laboratory will enable IBM researchers to collaborate on a daily basis with MILA faculty, staff and students on core AI technology projects. 'Thanks to this new structure, we will be able to strengthen our relationship with MILA and participate even more actively in the development of Montreal's growing deep-learning ecosystem,' said Bowen Zhou, director of IBM's AI Foundations projects and chief scientist of its Watson platform. 'My team and I are looking forward to this extended collaboration with IBM's researchers here in Montreal where a great community of academics and entrepreneurs are working together to shape the future of AI,' said Professor Bengio.

Apple's director of artificial intelligence, Ruslan Salakhutdinov, believes that the deep neural networks that have produced spectacular results in recent years could be supercharged in coming years by the addition of memory, attention, and general knowledge. Speaking at MIT Technology Review's EmTech Digital conference in San Francisco on Tuesday, Salakhutdinov said these attributes could help solve some of the outstanding problems in artificial intelligence. Salakhutdinov, who retains a post as an associate professor at Carnegie Mellon University in Pittsburgh, pointed in his talk to limitations with deep-learning-driven machine vision and natural-language understanding. Deep learning--a technique that involves using vast numbers of roughly simulated neurons arranged in many interconnected layers--has produced dramatic progress in machine perception over recent years, but there are many ways in which these networks are limited. Salakhutdinov showed, for example, how image captioning systems based on the technology can label images incorrectly because they tend to focus on everything in the image.

We introduce Parseval networks, a form of deep neural networks in which the Lipschitz constant of linear, convolutional and aggregation layers is constrained to be smaller than 1. Parseval networks are empirically and theoretically motivated by an analysis of the robustness of the predictions made by deep neural networks when their input is subject to an adversarial perturbation. The most important feature of Parseval networks is to maintain weight matrices of linear and convolutional layers to be (approximately) Parseval tight frames, which are extensions of orthogonal matrices to non-square matrices. We describe how these constraints can be maintained efficiently during SGD. We show that Parseval networks match the state-of-the-art in terms of accuracy on CIFAR-10/100 and Street View House Numbers (SVHN), while being more robust than their vanilla counterpart against adversarial examples. Incidentally, Parseval networks also tend to train faster and make a better usage of the full capacity of the networks.

Due to the recent achievements of artificial neural networks across many different tasks (such as face recognition, object detection and Go), deep learning has become extremely popular. This post aims to be a starting point for those interested in learning more about it. If you already have a basic understanding of linear algebra, calculus, probability and programming: I recommend starting with Stanford's CS231n. The course notes are comprehensive and well-written. The slides for each lesson are also available, and even though the accompanying videos were removed from the official site, re-uploads are quite easy to find online.

Deep learning is not a beginner-friendly subject -- even for experienced software engineers and data scientists. If you've been Googling this subject, you may have been confused by the resources you've come across. To find the best resources, we surveyed engineers on their favorite sources for deep learning, and these are what they recommended. These educational resources include online courses, in-person courses, books, and videos. All are completely free and designed by leading professors, researchers, and industry professionals like Geoffrey Hinton, Yoshua Bengio, and Sebastian Thrun.

Machine learning--Machine learning is arguably the most commonly found manifestation of cognitive computing, so it's not surprising it's available in so many forms. There is both supervised and unsupervised machine learning (the former of which requires human intervention and the latter of which learns on its own, according to Nanduri), as well as that centered upon automation and that centered upon recommendations. "When we think about how we're going to build machine learning into a workflow, we try to think hard about whether this is a recommendation problem or an automation problem," Eliot Knudsen, data science lead at Tamr (tamr.com), "It's a little subtle but tends to be important in framing the work we do." Deep learning--Deep learning and neural network techniques bear similarity to machine learning ones yet involve a degree of inferences and learning by examples--rather than in accordance with training based on predefined rules--that creates a profound difference.

Deep learning is a branch of machine learning, employing numerous similar, yet distinct, deep neural network architectures to solve various problems in natural language processing, computer vision, and bioinformatics, among other fields. Deep learning has experienced a tremendous recent research resurgence, and has been shown to deliver state of the art results in numerous applications. In essence, deep learning is the implementation of neural networks with more than a single hidden layer of neurons. This is, however, a very simplistic view of deep learning, and not one that is unanimously agreed upon. These "deep" architectures also vary quite considerably, with different implementations being optimized for different tasks or goals.

A whole bunch of incredible things have happened in Machine Learning and Artificial Intelligence since November. TensorFlow was a successor to their DistBelief technology that remained dependent on Google infrastructure, and hence wasn't ready to be open-sourced. However, TensorFlow was developed with the open source concept in mind. Some analysts believe that this strategy was similar to what Google adopted for Android. Open-sourced Android has grabbed 80% market share in the smartphone market.

A collaborative course incorporating labs in TensorFlow and peer brainstorming along with lectures.