In this paper we present a method for learning a discriminative classifier from unlabeled or partially labeled data. Our approach is based on an objective function that trades-off mutual information between observed examples and their predicted categorical class distribution, against robustness of the classifier to an adversarial generative model. The resulting algorithm can either be interpreted as a natural generalization of the generative adversarial networks (GAN) framework or as an extension of the regularized information maximization (RIM) framework to robust classification against an optimal adversary. We empirically evaluate our method - which we dub categorical generative adversarial networks (or CatGAN) - on synthetic data as well as on challenging image classification tasks, demonstrating the robustness of the learned classifiers. We further qualitatively assess the fidelity of samples generated by the adversarial generator that is learned alongside the discriminative classifier, and identify links between the CatGAN objective and discriminative clustering algorithms (such as RIM).

My secretary, Amy Ingram (AI – geddit?), is designed to help people organise their diaries and set up meetings. That's all she can do. But she goes about it in a freakishly human-like way. In fact, after using her for a couple of weeks, various contacts of mine – after communicating with her over email – said they had no idea she was not a real person. For her to do her job, you need to give her access to your electronic diary, set a few preferences (your three favourite coffee shops to meet in, for example), and copy her into any emails about meetings you want to set up.

This has been the year of the AI machine, and it's been a rapid change. Artificial intelligence has suddenly begun to match and even outperform humans in tasks where we've have always held the upper hand--face recognition, object recognition, language understanding and so on. And yet there are plenty of complex tasks in which AI machines still trail humans. These range from simple housework such as ironing to more advanced tasks such as driving. The reason for the slow progress in these areas is not that intelligent machines can't do these tasks.

DETROIT -- Fiat Chrysler CEO Sergio Marchionne says repeatedly that automakers must consider partnerships with other automakers and tech giants like Apple and Google. For those paying close attention over past year, reports that Fiat Chrysler Automobiles is in advanced discussions with Alphabet Inc.'s self-driving car division about a technology partnership is not a complete surprise. Marchionne, who also has courted General Motors for a mega-merger, has also met with Apple, Google and Tesla over the past year. FCA and Google declined to comment, but The Associated Press and the Wall Street Journal reported Thursday that the two companies are in advanced talks to form a technical partnership. The partnership would be the first to match an automaker with Google's 7-year-old autonomous car project, which is now part of the so-called X lab at Alphabet, Google's parent company.

A visitor to Mobile World Congress in Barcelona tries on a virtual-reality headset, one of a coming wave of VR devices. SAN FRANCISCO – I love watching people experience virtual reality for the first time. The cumbersome headsets exaggerate their movements as they scan left to right, and then nod up and down. And every time they look in another direction and spot something new, you can almost feel their amazement through the goggles. Lately, I feel as though I've put on a VR headset and never took it off. Because every time I turn, it seems, I spy something truly inspirational.

More than a week after his death, Prince is everywhere. Artists the world over counted him as an influence and mentor, and Japan is no exception. When news of Prince's death broke, Japanese musicians, from pop idols to rappers, tweeted their goodbyes. But what a lot of people may not realize is that Prince also had profoundly affected one of the most bizarre comic and anime franchises Japan has ever produced – a series called, appropriately enough, "Jojo's Bizarre Adventure." The series isn't quite as popular as titles like "One Piece" or "Dragon Ball Z," but it has been running since 1985, spawned video game and novel spinoffs and produced a serious cult following.

There are two fundamental milestones I'd say. The first one is Fisher's Linear Discriminant [1], later generalized by Rao [2] to what we know as Linear Discriminant Analysis (LDA). Essentially, LDA is a linear transformation (or projection) technique, which is mainly used for dimensionality reduction (i.e., the objective is to find the k-dimensional feature subspace that -- linearly -- separates the samples from different classes best. Given the objective to maximize class separability, projecting the 2D dataset below onto "x-axis component," would be a better choice than the "y-axis component." Keep in mind though that LDA is a projection technique; the feature axes of your new feature subspace are (almost certainly) different from your original axes.

Sometime recently the world of healthcare quietly changed and not many people noticed. IBM's artificially intelligent supercomputer Watson decided that it's (his?) prowess at Jeopardy was nothing more than a neat parlour trick and went to med school. Forbes reported that Watson waded through textbooks, medical databases PubMed and Medline and copious quantities of patient records from leading hospitals. "Watson has analysed 605,000 pieces of medical evidence, 2 million pages of text, 25,000 training cases and had the assist of 14,700 clinician hours fine-tuning its decision accuracy," according to Forbes. Supporters now claim that Dr. Watson is now the world's best diagnostician with consistent, accurate diagnoses based on access to essentially all known medical wisdom.

Storm damage repairs and preventative maintenance on power lines and trees are two of the most important tasks utility companies take on, requiring a large amount of time and budget. Currently, ground crews inspect assets manually or via helicopter, and then based on their observations, they'll identify areas that need attention. New technology on the horizon will help protect the grid from potentially dangerous storms and trees that pose a risk of falling. Affordable drone technology, coupled with big data software, is paving the way for a more detailed, holistic approach to storm damage assessment and utility maintenance. Through the collaboration of Edison Electric Institute and Palo Alto-based drone service company Sharper Shape, the EEI Sharper Utility partnership was formed to fast-track long-distance commercial drone inspections of power lines in the U.S. Drone flights have already found their footing in Europe with help from Sharper Shape's European affiliate and are looking to make an impact on the utility industries in the U.S. and the rest of the world.

So far I have talked about decision trees and ensembles. But I hope, I have made you understand the logic behind these concepts without getting too much into the mathematical details. In this post lets get into action, I will be implementing the concepts that we learned in these two blog posts. The only concept that I haven't discussed about is SVM. I suggest you to watch Professor Andrew Ng's week 7 videos on Coursera.