Artificial Intelligence (AI) is the cutting edge in technology. It is fast getting mainstream and coming out of the confines of science fiction. The onset of AI-based technology in India is evident in the sectors of e-commerce and research, where entities that are already using data analytics, are now looking to explore AI. I got great perspectives on the potential of AI at Intel's AI Day at Bangalore recently. I also got to know the various parts that make up AI and why it is so complex.

In the tech space, these terms have been used a lot and sometimes interchangeably without understanding what they mean. So what is all the fuss about? Before we get to why you should care, let us first clear up the confusion of what each is all about and how it came to be. AI is simply human intelligence expressed by a machine. Well of course not, human intelligence on its own is a complex thing and replicating it is no easy task.

In the past few months I've been fascinated with "Deep Learning", especially its applications to language and text. I've spent the bulk of my career in financial technologies, mostly in algorithmic trading and alternative data services. You can see where this is going. I wrote this to get my ideas straight in my head. While I've become a "Deep Learning" enthusiast, I don't have too many opportunities to brain dump an idea in most of its messy glory.

Deep Learning has become a worldwide phenomenon with it being applied to everything, from healthcare to autonomous vehicles to the world of finance. With the Deep Learning Summit, we have been able to meet data scientists, CTO's, influential technologists from all around the world and see how they have been developing and applying deep learning. We asked some of the RE•WORK community to tell us how they said Deep Learning in their language. Let us know how you say it!

A toolkit used across Microsoft to achieve breakthroughs in artificial intelligence is generally available to the public via an open-source license, a team of researchers and software engineers announced today. "The 2.0 version of the toolkit is now in full release," said Chris Basoglu, a partner engineering manager at Microsoft. He has played a key role in developing Microsoft Cognitive Toolkit (previously known as CNTK). The full release of Microsoft Cognitive Toolkit 2.0 for use in production-grade and enterprise-grade deep learning workloads includes hundreds of new features incorporated since the beta to streamline the process of deep learning and to ensure the toolkit's seamless integration throughout the wider AI ecosystem. New with the full release today is support for Keras, a user-friendly open-source neural network library that is popular with developers working on deep learning applications.

Alzheimer's disease is a major cause of dementia. Its diagnosis requires accurate biomarkers that are sensitive to disease stages. In this respect, we regard probabilistic classification as a method of designing a probabilistic biomarker for disease staging. Probabilistic biomarkers naturally support the interpretation of decisions and evaluation of uncertainty associated with them. In this paper, we obtain probabilistic biomarkers via Gaussian Processes. Gaussian Processes enable probabilistic kernel machines that offer flexible means to accomplish Multiple Kernel Learning. Exploiting this flexibility, we propose a new variation of Automatic Relevance Determination and tackle the challenges of high dimensionality through multiple kernels. Our research results demonstrate that the Gaussian Process models are competitive with or better than the well-known Support Vector Machine in terms of classification performance even in the cases of single kernel learning. Extending the basic scheme towards the Multiple Kernel Learning, we improve the efficacy of the Gaussian Process models and their interpretability in terms of the known anatomical correlates of the disease. For instance, the disease pathology starts in and around the hippocampus and entorhinal cortex. Through the use of Gaussian Processes and Multiple Kernel Learning, we have automatically and efficiently determined those portions of neuroimaging data. In addition to their interpretability, our Gaussian Process models are competitive with recent deep learning solutions under similar settings.

PyData London 2017 Description This talk will demonstrate how to harness a deep-learning framework such as Tensorflow, together with the usual suspects such as Pandas and Numpy, to implement recommendation models for news and classified ads. Abstract Recommender systems are used across the digital industry to model users' preferences and increase engagement. Popularised by the seminal Netflix prize, collaborative filtering techniques such as matrix factorisation are still widely used, with modern variants using a mix of meta-data and interaction data in order to deal with new users and items. We will demonstrate how to implement a variety of models using Tensorflow, from simple bi-linear models expressed as shallow neural nets to the latest deep incarnations of Amazon DSSTNE and Youtube neural networks. We will also use TensorBoard and particularly the embedding projector to visualise the latent space for items and metadata.

Deep learning is affecting the way we interact with technology. Fortune's article, "Why Deep Learning is Suddenly Changing your Life", describes how deep learning is responsible for the immense improvements in many applications, from voice recognition to language translation. Deep learning is a form of artificial intelligence that teaches computers to learn by example. Deep learning models, trained by using a large set of labeled data and neural network architectures that contain many layers, routinely achieve impressive accuracy. The combination of large sets of labeled data and advances in computing power has enabled deep learning to impact many industries, from automated driving to medical devices.

Like the hackathon, the code challenge is to build a machine learning based signal classifier that can be used for observations made in real time at the Allen Telescope Array (ATA). The winning classifier of the code challenge will be implemented at the ATA and become part of the data analysis pipeline. The challenge will last from June 1 to July 31st. Submitted entries will be judged based on their classification accuracy, accuracy for low-amplitude signals, and speed of single event classification. More details will be provided later about how to submit your work. THIS IS THE EVENTBRITE FOR THE HACKATHON ONLY! YOU MUST REGISTER FOR THE CODE CHALLENGE SEPARATELY The hackathon in San Francisco is a kick-off event for the code challenge (See below for info on the separate prizes being awarded for each event.)

Here is our selection of featured articles and resources published since Monday.