Image understanding using deep convolutional network has reached human-level performance, yet a closely related problem of video understanding especially, action recognition has not reached the requisite level of maturity. We combine multi-kernels based support-vector-machines (SVM) with a multi-stream deep convolutional neural network to achieve close to state-of-the-art performance on a 51-class activity recognition problem (HMDB-51 dataset); this specific dataset has proved to be particularly challenging for deep neural networks due to the heterogeneity in camera viewpoints, video quality, etc. The resulting architecture is named pillar networks as each (very) deep neural network acts as a pillar for the hierarchical classifiers. In addition, we illustrate that hand-crafted features such as improved dense trajectories (iDT) and Multi-skip Feature Stacking (MIFS), as additional pillars, can further supplement the performance.

Artificial intelligence (AI), deep learning, and neural networks represent incredibly exciting and powerful machine learning-based techniques used to solve many real-world problems. For a primer on machine learning, you may want to read this five-part series that I wrote. While human-like deductive reasoning, inference, and decision-making by a computer is still a long time away, there have been remarkable gains in the application of AI techniques and associated algorithms. The concepts discussed here are extremely technical, complex, and based on mathematics, statistics, probability theory, physics, signal processing, machine learning, computer science, psychology, linguistics, and neuroscience. That said, this article is not meant to provide such a technical treatment, but rather to explain these concepts at a level that can be understood by most non-practitioners, and can also serve as a reference or review for technical folks as well.

True, everyone born before Aug. 4, 1900, has proved mortal (the world's oldest-known living person, a Japanese woman named Nabi Tajima, was born on that date). But the past is only an imperfect guide to the future, as the effervescent present is ceaselessly teaching us. But our children, our grandchildren -- or if not them, theirs -- may, conceivably, be the beneficiaries of the greatest revolution ever: the conquest of death. Immortality is an ancient dream. A Chinese king of the third century B.C. dispatched a sage, Xu Fu by name, on a quest for the elixir of life.

For Peter Cao, who has dedicated 16 years of his career to teaching chemistry in a high school in central China's Anhui province, in every teacher there lives a "doctor". He spends two to three hours a day grading assignments, a process the 38-year-old describes as "diagnosing". "By reviewing the homework of my pupils, I can have an overall picture about their understanding of the lessons I give," Cao said, adding that this "diagnosis" helps him draw up a teaching plan for the following day. But if the Chinese online education start-up Master Learner has its way, Cao and his 14 million fellow teachers in China will be able to hand this time-consuming review process to a "super teacher", a powerful "brain" capable of answering nearly 500 million of the most tested questions in China's middle schools as well as scoring high points in each Gaokao test, China's life-changing college entrance exam, for the past 30 years. If the super teacher sounds too smart to be human, that is because it is not.

BDA Goes … continued • "… using Big and Smart Data as well as methods and tools based on semantic technologies will provide more transparency, enable precise and well-founded decisions and improve planning processes, which will result in more efficient and user-centric processes and systems …" • "Integrating things, data and semantic opens opportunities for knowledge discovery, and further makes it possible to provide advanced and intelligent services."

At first blush, Scot Barton might not seem like an AI pioneer. He isn't building self-driving cars or teaching computers to thrash humans at computer games. But within his role at Farmers Insurance, he is blazing a trail for the technology. Barton leads a team that analyzes data to answer questions about customer behavior and the design of different policies. His group is now using all sorts of cutting-edge machine-learning techniques, from deep neural networks to decision trees.

This webinar will demonstrate how to use the new Azure ML Workbench to solve complicated NLP tasks such as entity extraction from unstructured text. The tutorial aims to analyze a large corpus of unlabeled unstructured text records such as Medline PubMed abstracts and trains a word embedding model. The output embeddings are considered as automatically generated semantic features to train a neural entity extractor. We systematically show how to train a word embeddings model using word2vec neural word embedding algorithm with nearly 20 million Medline article abstracts on an HDInsight Spark cluster and then use the auto-generated features to train a LSTM deep recurrent neural network for medical entity extraction on a GPU-equipped Data Science Virtual Machine.

We consider first order gradient methods for effectively optimizing a composite objective in the form of a sum of smooth and, potentially, non-smooth functions. We present accelerated and adaptive gradient methods, called FLAG and FLARE, which can offer the best of both worlds. They can achieve the optimal convergence rate by attaining the optimal first-order oracle complexity for smooth convex optimization. Additionally, they can adaptively and non-uniformly re-scale the gradient direction to adapt to the limited curvature available and conform to the geometry of the domain. We show theoretically and empirically that, through the compounding effects of acceleration and adaptivity, FLAG and FLARE can be highly effective for many data fitting and machine learning applications.

Using Keras to train deep neural networks with multiple GPUs (Photo credit: Nor-Tech.com). Keras is undoubtedly my favorite deep learning Python framework, especially for image classification. I use Keras in production applications, in my personal deep learning projects, and here on the PyImageSearch blog. I've even based over two-thirds of my new book, Deep Learning for Computer Vision with Python on Keras. However, one of my biggest hangups with Keras is that it can be a pain to perform multi-GPU training.

Approximately 658 corporate decision makers have been surveyed for their confidence in their own decision-making skills and their acceptance of the importance of Artificial Intelligence (A.I.) in general as well as in augmenting (or replacing) their decision making. Furthermore, the survey reveals the general perception of the corporate data-driven environment available to decision maker, e.g., the structure and perceived quality of available data. A comprehensive overview and analysis of our AI sentiments as it relates to corporate decision making is provided as a function Gender, Age, Job-level, Work area and Education. You don't need to make an effort to find articles, blogs, social media postings, books and insights in general on how Artificial Intelligence (hereafter abbreviated A.I.) will provide wonders for all human beings, society and leapfrog corporate efficiencies and shareholder values for the ones adapting to A.I. (of which you would be pretty silly not too of course).