I recently completed a course on NLP through Deep Learning (CS224N) at Stanford and loved the experience. For my final project I worked on a question answering model built on Stanford Question Answering Dataset (SQuAD). In this blog, I want to cover the main building blocks of a question answering model. You can find the full code on my Github repo. Stanford Question Answering Dataset (SQuAD) is a new reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage.

Deep learning is the next big thing. Its favorable results in applications with huge and complex data is remarkable. R programming language is very popular among data miners and statisticians. Deep learning refers to artificial neural networks that are composed of many layers. Deep learning is a powerful set of techniques for finding accurate information from raw data.

In this tutorial, we provide step-by-step instructions to go from loading a pre-trained Convolutional Neural Network model to creating a containerized web application that is hosted on Kubernetes cluster with GPUs on Azure Container Service (AKS). AKS makes it quick and easy to deploy and manage containerized applications without much expertise in managing Kubernetes environment. It eliminates complexity and operational overhead of maintaining the cluster by provisioning, upgrading, and scaling resources on demand, without taking the applications offline. AKS reduces the cost and complexity of using a Kubernetes cluster by managing the master nodes for which the user does no incur a cost. Azure Container Service has been available for a while and similar approach was provided in a previous tutorial to deploy a deep learning framework on Marathon cluster with CPUs .

Intelligence agents and military operatives may come to rely heavily on Machine Learning and Artificial Intelligence (AI) to parse huge quantities of data, and to control a growing arsenal of autonomous systems, but the US Military wants to make sure that this doesn't lead to blindly trusting algorithms, that even though there are a couple of tests to assess how dangerous they are, or could become, are still at their heart mysterious black boxes. As a result the Defense Advanced Research Projects Agency (DARPA), a division of the US Defense Department that explores new technologies, is following the lead shown by Columbia University, MIT, and Nvidia, who have all been trying to develop new systems that read AI's minds and get them to explain their decision making processes, and they've announced they're going to be funding several new projects. The approaches range from adding further machine learning systems geared toward providing an explanation, to the development of new machine learning approaches that incorporate an "elucidation by design." "We now have this real explosion of AI," says David Gunning, the DARPA program manager who is funding an effort to develop AI techniques that include some explanation of their reasoning, "the reason for that is mainly machine learning, and deep learning in particular." Deep learning and other machine learning techniques have taken Silicon Valley by storm, improving voice recognition and image classification significantly, and they are being used in more contexts than ever before, including areas like law enforcement and medicine, where the consequences of a mistake may be serious.

There is no typecast for savvy AI businesses. They come in all sizes and represent an ever broadening swath of industry. Simply put, the era of artificial intelligence is remaking business as we know it. Businesses see AI as a long-term strategic priority. In a recent survey from Infosys, three-quarters of the respondents from large, multinational corporations cited AI as fundamental to the success of their organization's strategy.

When we are in the outdoors, many of us often feel the need for a camera- that is intelligent enough to follow us, adjust to the terrain heights and visually navigate through the obstacles, while capturing panoramic videos. Here, I am talking about autonomous self-flying drones, very similar to cars on auto pilot. The difference is that we are starting to see proliferation of artificial intelligence into affordable, everyday use cases, compared to relatively expensive cars. This helps them distinguish between objects and get better with more data. Recently, Roni Fontaine at Hortonworks published a blog titled "How Apache Hadoop 3 Adds Value Over Apache Hadoop 2", capturing the high-level themes.

Elon Musk's OpenAI is paying big money for the world's best AI researchers. There's been a lot of speculation in the last couple of years about how much money technology firms are paying the world's top artificial intelligence (AI) experts but concrete numbers have been hard to come by. That changed this week when Cade Metz, a journalist for The New York Times, revealed that he had stumbled upon a tax filing from OpenAI -- an AI research lab set up by Tesla CEO Elon Musk -- that included staff salaries and bonuses. The numbers are high, especially when you consider the fact that Open AI is a non-profit organisation. The company, which says it is working to ensure AI benefits all of humanity, was founded in San Francisco in 2015.

This post is a step by step guide through the paper. We'll cover the technical details and also walk through how you can get a version running on your own machine. Similarly to my post on AlphaZero, I'm not associated with the authors of the paper but just wanted to share my interpretation of their terrific work. We're going to build a reinforcement learning algorithm (an'agent') that gets good at driving a car around a 2D racetrack. At each time-step, the algorithm is fed an observation (a 64 x 64 pixel colour image of the car and immediate surroundings) and needs to return the next set of actions to take -- specifically, the steering direction (-1 to 1), acceleration (0 to 1) and brake (0 to 1). This action is then passed to the environment, which returns the next observation and the cycle starts again.

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.

Deep Learning has taken the world of Computer Science by storm yet for many of us it remains an elusive sci-fi-like buzzword. After years of feature engineering in Computer Vision and Natural Language Processing, we have finally come to the point where, we can feed raw data to a Neural Network, similar to how our brains work, and expect results that can surprise us in their high accuracy. This talk is about de-mystifying Deep Learning for developers many of whom could benefit from understanding and using Deep Learning in their day-to-day job. It covers the background and brief theoretical grounds in the first half but shows actual working code and examples in the rest. We will overview convolutional Neural Networks and then cover network design techniques such as pooling, dropout and local connections. The examples of this talk are in Keras on top of TensorFlow and aimed to build real-world models in the field of Text Processing.