This is made possible by incredible advances in a wide range of technologies, from computation to interconnect to storage, and innovations in software libraries, frameworks, and resource management tools. While there are many critical challenges, an open technology approach provides significant advantages. The Scaling Challenge The full deep learning story, though, must be an end-to-end technology discussion and encompass production at scale. As we scale out deep learning workloads to the massive compute clusters required to tackle these big issues, we begin to run into the same challenges that hamper scaling of traditional high-performance computing (HPC) workloads. Ensuring optimal use of compute resources can be challenging, particularly in heterogeneous architectures that may include multiple central processing unit (CPU) architectures, such as x86, ARM64, and Power, as well as accelerators, such as graphical processing units (GPUs), field programmable gate arrays (FPGAs), tensor processing units (TPUs), etc. Architecting an optimal deep learning solution for training or inferencing, with potentially varied data types, can result in the application of one or more of these architectures and technologies. The flexibility of open technologies allows one to deploy the optimal platform at server, rack, and data center scales.

Due to the lack of enough generalization in the state-space, common methods in Reinforcement Learning (RL) suffer from slow learning speed especially in the early learning trials. This paper introduces a model-based method in discrete state-spaces for increasing learning speed in terms of required experience (but not required computational time) by exploiting generalization in the experiences of the subspaces. A subspace is formed by choosing a subset of features in the original state representation (full-space). Generalization and faster learning in a subspace are due to many-to-one mapping of experiences from the full-space to each state in the subspace. Nevertheless, due to inherent perceptual aliasing in the subspaces, the policy suggested by each subspace does not generally converge to the optimal policy. Our approach, called Model Based Learning with Subspaces (MoBLeS), calculates confidence intervals of the estimated Q-values in the full-space and in the subspaces. These confidence intervals are used in the decision making, such that the agent benefits the most from the possible generalization while avoiding from detriment of the perceptual aliasing in the subspaces. Convergence of MoBLeS to the optimal policy is theoretically investigated. Additionally, we show through several experiments that MoBLeS improves the learning speed in the early trials.

The ocean is indeed a strange place, but Whitman might not have found it quite so confounding if he'd had access to deep learning. This technology is allowing machines to do everything from disease diagnosis to musical composition to playing video games. Now, a team of scientists and engineers at the IBM Research lab in Dublin have set deep learning on that harshest of mistresses: the sea. Their deep-learning framework for simulating ocean waves enables real-time wave condition forecasts for a fraction of the traditional computational cost. How are wave forecasts traditionally calculated?

A critical element of change leadership is "going slow to go fast", but sometimes leaders need a short, sharp focus to generate professional learning conversations or for individual reflection. Designed as "quick shots", "Leadables" are intended to be used to provoke dialogue and focussed conversations around a variety of Leading, Teaching and Learning elements. Themes will be drawn from examples we are seeing in schools and organizations, questions we are encountering and new ideas and research around deep learning. Click here to access Leadable 1.1 – Trusty Tools, which focuses on how we can use the NPDL Learning Progressions.

Diversity was a central theme in the ACM SIGIR 2017 held in Shinjuku Ward in Tokyo, Japan. Fuji, a view of Shinjuku sky-scrapers, including the Tokyo Metropolitan Government (Office), as seen from Keio Plaza the conference hotel, and fireworks celebrating the 40th anniversary. The colorfulness of the fireworks and the circles within and enclosing the logo represent diversity and inclusion." SIGIR 2017 featured a session on Women in IR (Information Retrieval) organized by Laura Dietz of the University of New Hampshire on the first day, just before the welcome party. A week before the conference, I received an email from the secretary of the session, Maram Hasanain, a graduate student in computer science (CS) at Qatar University, asking if I would like to prepare a one-minute introduction of myself for the session. I was so overwhelmed by her beautifully written e-mail, and the excitement of a first-time contact with someone from Qatar, that I immediately accepted her invitation.

The Intel Nervana AI Academy for Students program was created to work collaboratively with students at innovative schools and universities doing great work in the Machine Learning and Artificial Intelligence space. I had the opportunity to get to know Intel Student Ambassador Karandeep Singh Dhillon and learn about how he became interested in deep learning and how he wants to make it easy for anyone to understand and apply to real-life situations. Tell us about your background and what got you started in technology. My parents bought me a computer when I was in 6th grade and by the time I was in 8th grade would make small Bash programs to help me automate tasks. I loved to create those small programs and I decided that I wanted to learn more and would take Computer Science courses for my undergraduate degree.

Artificial Intelligence (AI) and Machine Learning (ML) are some of the hottest topics right now. The term "AI" is thrown around casually every day. You hear aspiring developers saying they want to learn AI. You also hear executives saying they want to implement AI in their services. But quite often, many of these people don't understand what AI is.

Tech startups have always had a recruiting advantage over the industry's giants: Take a chance on us and we'll give you an ownership stake that could make you rich if the company is successful. Now the tech industry's race to embrace artificial intelligence may render that advantage moot -- at least for the few prospective employees who know a lot about AI. Tech's biggest companies are placing huge bets on artificial intelligence, banking on things ranging from face-scanning smartphones and conversational coffee-table gadgets to computerized health care and autonomous vehicles. As they chase this future, they are doling out salaries that are startling even in an industry that has never been shy about lavishing a fortune on its top talent. Typical AI specialists, including both Ph.D.s fresh out of school and people with less education and just a few years of experience, can be paid from $300,000 to $500,000 a year or more in salary and company stock, according to nine people who work for major tech companies or have entertained job offers from them.

Caltech professor Aaron Ames walks on campus alongside Cassie, a semi-autonomous robot, as doctoral student Jacob Reher, left, controls the direction that Cassie travels. The robot's balance and gait are autonomous. Caltech professor Aaron Ames walks on campus alongside Cassie, a semi-autonomous robot, as doctoral student Jacob Reher, left, controls the direction that Cassie travels. The robot's balance and gait are autonomous. The mechanical "clack, clack, clack" of an orange robot on the march brought Caltech's new indoor drone arena to life.

Now, Google has declared that AutoML has defeated the human AI engineers at their own game by setting machine-learning software that's more effective and powerful than the best human-designed systems. An AutoML system recently broke a record for classifying perceptions by their content, scoring 82 percent. While that's a relatively simple task, AutoML also beat the single-built system at a more complex task key to autonomous robots and augmented reality: showing the location of multiple objects in an image. For that task, AutoML scored 43 percent versus the individual-built system's 39 percent. These results are important because even at Google, few people have the needed expertise to build next-generation AI systems.