Algorithm design is a laborious process and often requires many iterations of ideation and validation. In this paper, we explore automating algorithm design and present a method to learn an optimization algorithm, which we believe to be the first method that can automatically discover a better algorithm. We approach this problem from a reinforcement learning perspective and represent any particular optimization algorithm as a policy. We learn an optimization algorithm using guided policy search and demonstrate that the resulting algorithm outperforms existing hand-engineered algorithms in terms of convergence speed and/or the final objective value.

We present a generic compact computational framework relying on structured random matrices that can be applied to speed up several machine learning algorithms with almost no loss of accuracy. The applications include new fast LSH-based algorithms, efficient kernel computations via random feature maps, convex optimization algorithms, quantization techniques and many more. Certain models of the presented paradigm are even more compressible since they apply only bit matrices. This makes them suitable for deploying on mobile devices. All our findings come with strong theoretical guarantees. In particular, as a byproduct of the presented techniques and by using relatively new Berry-Esseen-type CLT for random vectors, we give the first theoretical guarantees for one of the most efficient existing LSH algorithms based on the $\textbf{HD}_{3}\textbf{HD}_{2}\textbf{HD}_{1}$ structured matrix ("Practical and Optimal LSH for Angular Distance"). These guarantees as well as theoretical results for other aforementioned applications follow from the same general theoretical principle that we present in the paper. Our structured family contains as special cases all previously considered structured schemes, including the recently introduced $P$-model. Experimental evaluation confirms the accuracy and efficiency of TripleSpin matrices.

After robots flood the work market, the only jobs left for real people will be those that require critical thinking and human-level care. Something like a teacher at a college, that could definitely never be outsourced to an machine, right? Ashok Goel, a professor in computing at Georgia Tech, implemented an artificial intelligence teaching assistant in the online Q&A forums for one of his courses last semester. Young academics busting their backs in hopes of one day snagging a TA job will be alarmed to learn that the A.I, named Jill, performed so well that most of the course's students couldn't tell her from the other eight human TAs who were performing the same duties. The A.I.'s full name was Jill Watson, built from the same IBM Watson platform that beat humans in Jeopardy!

Rich Sutton is old school king of RL.

This is a very incomplete and subjective selection of resources to learn about the algorithms and maths of Artificial Intelligence (AI) / Machine Learning (ML) / Statistical Inference (SI) / Deep Learning (DL) / Reinforcement Learning (RL) -- for beginners. It is not an exhaustive list and only contains some of the learning materials that I have personally completed so that I can include brief personal comments on them. It is also by no means the best path to follow (nowadays most MOOCs have full paths all the way from basic statistics and linear algebra to ML/DL). But this is the path I took and in a sense it's a partial documentation of my personal journey into DL (actually I bounced around all of these back and forth like crazy). As someone who has no formal background in Computer Science (but has been programming for many years), the language, notation and concepts of ML/SI/DL and even CS was completely alien to me, and the learning curve was not only steep, but vertical, treacherous and slippery like ice.

This week's top Machine Learning stories, including AI agents that compose music, watch movies, surf Facebook, and more! Machine Learning is one of the most exciting fields in the world. Every week we discover something new, something amazing, something revolutionary. It's incredible, but it can also be overwhelming. That's why we created This Week in Machine Learning!

Getting ready for a job interview has been likened to everything from preparing for battle, to gearing up to ask someone out on a date, to lining up a putt on the 18th green at The Masters. Preparing for a Machine Learning interview is no different. You know you've got something ahead with the potential to be either really great, or really terrible. But how do you ensure your result is the great one? Understanding the context of your pending interview--i.e. the reason WHY there's an open role in the first place--should be an integral part of your preparation.

People waste a lot of time if don't know the proper way of dealing with machine learning problem. Here is a very good and quick rule of thumb by Andrew Ng that can rescue any machine learning trainer if he/she is not getting improvement in model. First check whether model is suffering from'High Bias' or'High Variation' then try any of the following method to fix the issue. It is useful to plot a learning curve to understand if there is a high bias or high variance problem.

In this demo-rich course, led by entertaining experts Buck Woody, Seayoung Rhee, and Scott Klein, get a real-world look at the different ways you can efficiently embed predictive analytics in your big data solutions, and explore best practices for analyzing trends and patterns. Find out about extending Azure ML using the Azure ML API services, and look at scenarios and methods for monetizing your ML application with Azure Marketplace. Instructor Seayoung Rhee - Microsoft Senior Technical Product Manager; Buck Woody - Microsoft Senior Technical Specialist; Scott Klein - Microsoft Senior Technical Evangelist Introduction to Machine Learning & Azure ML Studio Learn the meaning of Machine Learning and its benefits, and get a quick introduction to basic techniques. See a demo of the Azure Machine Learning portal, and tour the ML Studio. Designing a Predictive Analytics Solution with Azure ML Watch an end-to-end scenario demo, and recreate a recommendation model from scratch in ML Studio.

Our most powerful 21st-century technologies – robotics, genetic engineering, and nanotech – are threatening to make humans an endangered species. From the moment I became involved in the creation of new technologies, their ethical dimensions have concerned me, but it was only in the autumn of 1998 that I became anxiously aware of how great are the dangers facing us in the 21st century. I can date the onset of my unease to the day I met Ray Kurzweil, the deservedly famous inventor of the first reading machine for the blind and many other amazing things. This article has been reproduced in a new format and may be missing content or contain faulty links. Contact wiredlabs@wired.com to report an issue. Ray and I were both speakers at George Gilder's Telecosm conference, and I encountered him by chance in the bar of the hotel after both our sessions were over. I was sitting with John Searle, a Berkeley philosopher who studies consciousness. While we were talking, Ray approached and a ...