Google announces scholarship program to train 1.3 lakh Indian developers in emerging technologies 43569 views Want to be a millionaire before you turn 25? Study artificial intelligence or machine learning 42897 views

First, it was the AlphaGo AI from Google's DeepMind subsidiary which beat the world's best Go players at their own game to make a record. Then, an AI named Libratus, developed by the Carnegie Mellon University, outclassed Poker pros in a tournament to turn the world's attention towards the rapid pace at which AI is progressing. In the latest such example of an AI outsmarting human beings, a deep neural network model developed by Alibaba fared better than humans in a reading comprehension test. The AI model developed by Alibaba's Institute of Data Science and Technologies blazed past the SQuAD (Stanford Question Answering Dataset) test- one of the most reliable reading comprehension test for evaluating a machine's language skills- in a contest which pitted it against human rivals. Alibaba's AI scored a cumulative 82.44 Exact Match (EM) points, outscoring its human competitors who manged to put up 82.304 points on the scoreboard.

The classification of complex data usually requires the composition of processing steps. Here, a major challenge is the selection of optimal algorithms for preprocessing and classification (including parameterizations). Nowadays, parts of the optimization process are automized but expert knowledge and manual work are still required. We present three steps to face this process and ease the optimization. Namely, we take a theoretical view on classical classifiers, provide an approach to interpret the classifier together with the preprocessing, and integrate both into one framework which enables a semiautomatic optimization of the processing chain and which interfaces numerous algorithms.

A general Data Science workflow in machine learning consists of the following steps: gather data, clean and prepare data, train models and choose the best model based on validation and test errors or other performance criteria. Usually we – particularly we Data Scientists or Statisticians who live for numbers, like small errors and high accuracy – tend to stop at this point. Let's say we found a model that predicted 99% of our test cases correctly. In and of itself, that is a very good performance and we tend to happily present this model to colleagues, team leaders, decision makers or whoever else might be interested in our great model. We assume that our model is trustworthy, because we have seen it perform well, but we don't know why it performed well.

This guide to meant to help web developers, software engineers and other IT industry people to transition into analytics / data science industry. Last week, I was taking a guest lecture with one of the well known institutes in India. Rather (un)surprisingly, more than 60% of the students comprised of experienced IT Professionals. Most of them are facing a common problem, "I have been in IT / software / web development for more than a few years and want to up-skill myself in analytics. I have taken a few MOOCs and have tried using a few books / platforms. Still, I don't get it what should I do next?"

Nigel Toon, chief executive, said the UK's expertise in artificial intelligence should help. Other entrepreneurs argue that the government should do more to help. Last year, ministers outlined plans for a new "office of AI" and said the government would invest £45m to fund post graduate degrees in the field …

In less than five years, artificial intelligence -- AI, as it's commonly known -- has gone from the stuff of science fiction to the forefront of the news, from scientific journals to the strategic plans of the world's biggest companies. It's a coming sea change, one that will disrupt entire parts of our lives by competing with what, until now, was seen as a fundamentally human characteristic: Our intelligence. At the same time, he acknowledges that AI -- at least for now -- is "still utterly unintelligent". Recognising a cat in a picture, a sentence dictated to a smartphone or even a tumour in MRI images is an impressive feat. But this prowess is still limited to very specific uses, Alexandre argues.

Since it launched in 2009, the Kepler Space Telescope has done a good job of collecting data -- too good for human analysis alone. The telescope has produced 14 billion data points about 200,000 stars. It has also amassed 35,000 signals indicating possible planets. People alone would not have been able to keep up. Since it launched in 2009, the Kepler Space Telescope has done a good job of collecting data -- too good for human analysis alone.

This post was written by Ofir Press. Ofir is a graduate student at Tel-Aviv University's Deep Learning Lab. His main focus is on using deep learning for natural language processing. "Due to the recent achievements of artificial neural networks across many different tasks (such as face recognition, object detection and Go), deep learning has become extremely popular. This post aims to be a starting point for those interested in learning more about it. If you already have a basic understanding of linear algebra, calculus, probability and programming: I recommend starting with Stanford's CS231n. The course notes are comprehensive and well-written. The slides for each lesson are also available, and even though the accompanying videos were removed from the official site, re-uploads are quite easy to find online. If you don't have the relevant math background: There is an incredible amount of free material online that can be used to learn the required math knowledge. Gilbert Strang's course on linear algebra is a great introduction to the field. For the other subjects, edX has courses from MIT on both calculus and probability. If you are interested in learning more about machine learning: Andrew Ng's Coursera class is a popular choice as a first class in machine learning. There are other great options available such as Yaser Abu-Mostafa's machine learning course which focuses much more on theory than the Coursera class but it is still relevant for beginners. Knowledge in machine learning isn't really a prerequisite to learning deep learning, but it does help. In addition, learning classical machine learning and not only deep learning is important because it provides a theoretical background and because deep learning isn't always the correct solution. Geoffrey Hinton's Coursera class "Neural Networks for Machine Learn... covers a lot of different topics, and so does Hugo Larochelle's "Neural Networks Class".

Democratization of content: In 2018, we will see more professionals outside of the training team contributing in creation of content. The concept of crowd sourcing will evolve in a big way with solution architects, professional services, and support organizations creating the content. Customers and partners will also contribute content as they implement the cloud computing solutions and identify new use cases and design and implementation best practices. This trend will see the role of training organizations evolving. Training teams will act more as a strategy and content curation arm providing tools and templates to the subject matter experts to develop the content and then curating the content.