A standard introduction to online learning might place Online Gradient Descent at its center and then proceed to develop generalizations and extensions like Online Mirror Descent and second-order methods. Here we explore the alternative approach of putting exponential weights (EW) first. We show that many standard methods and their regret bounds then follow as a special case by plugging in suitable surrogate losses and playing the EW posterior mean. For instance, we easily recover Online Gradient Descent by using EW with a Gaussian prior on linearized losses, and, more generally, all instances of Online Mirror Descent based on regular Bregman divergences also correspond to EW with a prior that depends on the mirror map. Furthermore, appropriate quadratic surrogate losses naturally give rise to Online Gradient Descent for strongly convex losses and to Online Newton Step. We further interpret several recent adaptive methods (iProd, Squint, and a variation of Coin Betting for experts) as a series of closely related reductions to exp-concave surrogate losses that are then handled by Exponential Weights. Finally, a benefit of our EW interpretation is that it opens up the possibility of sampling from the EW posterior distribution instead of playing the mean. As already observed by Bubeck and Eldan, this recovers the best-known rate in Online Bandit Linear Optimization.

IN JULY 2011 Sebastian Thrun, who among other things is a professor at Stanford, posted a short video on YouTube, announcing that he and a colleague, Peter Norvig, were making their "Introduction to Artificial Intelligence" course available free online. By the time the course began in October, 160,000 people in 190 countries had signed up for it. At the same time Andrew Ng, also a Stanford professor, made one of his courses, on machine learning, available free online, for which 100,000 people enrolled. Both courses ran for ten weeks. Such online courses, with short video lectures, discussion boards for students and systems to grade their coursework automatically, became known as Massive Open Online Courses (MOOCs).

Data science or data-driven science is one of today's fastest-growing fields. Are you looking for top Online courses on Data Science? Do you want to become a Data Scientist in 2017? Are you planning to buy a course for someone else to whom you do care? If your answer is yes, then you are in the right place.

One of the most challenging problems in kernel online learning is to bound the model size and to promote the model sparsity. Sparse models not only improve computation and memory usage, but also enhance the generalization capacity, a principle that concurs with the law of parsimony. However, inappropriate sparsity modeling may also significantly degrade the performance. In this paper, we propose Approximation Vector Machine (AVM), a model that can simultaneously encourage the sparsity and safeguard its risk in compromising the performance. When an incoming instance arrives, we approximate this instance by one of its neighbors whose distance to it is less than a predefined threshold. Our key intuition is that since the newly seen instance is expressed by its nearby neighbor the optimal performance can be analytically formulated and maintained. We develop theoretical foundations to support this intuition and further establish an analysis to characterize the gap between the approximation and optimal solutions. This gap crucially depends on the frequency of approximation and the predefined threshold. We perform the convergence analysis for a wide spectrum of loss functions including Hinge, smooth Hinge, and Logistic for classification task, and $l_1$, $l_2$, and $\epsilon$-insensitive for regression task. We conducted extensive experiments for classification task in batch and online modes, and regression task in online mode over several benchmark datasets. The results show that our proposed AVM achieved a comparable predictive performance with current state-of-the-art methods while simultaneously achieving significant computational speed-up due to the ability of the proposed AVM in maintaining the model size.

We consider revenue maximization in online auctions and pricing. A seller sells an identical item in each period to a new buyer, or a new set of buyers. For the online posted pricing problem, we show regret bounds that scale with the best fixed price, rather than the range of the values. We also show regret bounds that are almost scale free, and match the offline sample complexity, when comparing to a benchmark that requires a lower bound on the market share. These results are obtained by generalizing the classical learning from experts and multi-armed bandit problems to their multi-scale versions. In this version, the reward of each action is in a different range, and the regret w.r.t. a given action scales with its own range, rather than the maximum range.

Organizations like Insight Data science founded by Jake Klamka is specifically designed for helping PhD's transition into industry. At the other end of the spectrum, aspiring data scientists, who have enough domain expertise and are keen to pursue this art can take umbrage from the example of Clare Corthell who has embarked on a self crafted journey to embrace the art of data science purely on online learning MOOCs. In Fact she has herself come out with a curriculum for data science with the Open Source Data Science Masters--OSDSM- program. These courses can help you to bridge the gap in your learning and practicing the craft. The OSDSM is a collection of open source resources that will help you to acquire skills necessary to be a competent entry level data scientist. You can access the curriculum here . You have to be adept at learning and upgrading on the job and on the fly. Kunal Punera the Co founder / CTO at Bento labs talks about this aspect when he says.. I spent two years at RelateIQ. I worked on building the data mining system from scratch -- and by the time I left I had built most of the data products deployed in RelateIQ.

Jeremy P. Howard, @JeremyPHoward, is a leading Machine Learning and Deep learning researcher and entrepreneur. His current startup is fast.ai Previously, he was CEO and founder of Enlitic, Kaggle President, and #1 ranked Kaggle competitor. Jeremy initiatives attracts a lot of attention in the industry, so I was very interested to learn from him about his latest project, a first Deep Learning for coders MOOC at course.fast.ai. The course is totally free and includes no advertising - Jeremy created it purely as a service to the community.

Machines are eating humans' jobs talents. And it's not just about jobs that are repetitive and low-skill. Automation, robotics, algorithms and artificial intelligence (AI) in recent times have shown they can do equal or sometimes even better work than humans who are dermatologists, insurance claims adjusters, lawyers, seismic testers in oil fields, sports journalists and financial reporters, crew members on guided-missile destroyers, hiring managers, psychological testers, retail salespeople, and border patrol agents. Moreover, there is growing anxiety that technology developments on the near horizon will crush the jobs of the millions who drive cars and trucks, analyze medical tests and data, perform middle management chores, dispense medicine, trade stocks and evaluate markets, fight on battlefields, perform government functions, and even replace those who program software – that is, the creators of algorithms. People will create the jobs of the future, not simply train for them, ...

In a thrilling science talk, Kenneth Cukier looks at what's next for machine learning -- and human knowledge. Kenneth Cukier is the Data Editor of The Economist. From 2007 to 2012 he was the Tokyo correspondent, and before that, the paper's technology correspondent in London, where his work focused on innovation, intellectual property and Internet governance. Kenneth is also the co-author of Big Data: A Revolution That Will Transform How We Live, Work, and Think with Viktor Mayer-Schönberger in 2013, which was a New York Times Bestseller and translated into 16 languages. Kenneth Cukier is the Data Editor of The Economist.

A third to half the jobs that we are currently employed in would disappear in the next 15 years; and yet your child is being prepared in school for those very same jobs that won't exist by the time they graduate. Our curriculum prepares us for a lifetime career, but a child today can expect to change jobs at least seven times over the course of their lives – and five of those jobs don't exist yet. The coming days would see us pursuing careers that we cannot even imagine today. For instance your child could be an expert licensed drone pilot, or a cyber warrior in the army, a data analyst making sense of the peta bytes of data generated through our social interactions and trying to forecast our behavior. The other big challenge facing students today is that the velocity of technology changes has gained incredible speed; this is making knowledge obsolete faster than before.