Kaggle competitions are a fantastic way to learn data science and build your portfolio. I personally used Kaggle to learn many data science concepts. I started out with Kaggle a few months after learning programming, and later won several competitions. Doing well in a Kaggle competition requires more than just knowing machine learning algorithms. It requires the right mindset, the willingness to learn, and a lot of data exploration. Many of these aspects aren't typically emphasized in tutorials on getting started with Kaggle, though. In this post, I'll cover how to get started with the Kaggle Expedia hotel recommendations competition, including establishing the right mindset, setting up testing infrastructure, exploring the data, creating features, and making predictions.

Boston: In a latest discovery by the scientists, including one of Indian-origin, have developed artificial software that can turn smartphone in to an eye tracking device. Eye-tracking technology - which can determine where in a visual scene people are directing their gaze - has been widely used in psychological experiments and marketing research, but the required pricey hardware has kept it from finding consumer applications. In addition to making existing applications of eye-tracking technology more accessible, the system developed by researchers at Massachusetts Institute of Technology (MIT) and University of Georgia may enable new computer interfaces or help detect signs of incipient neurological disease or mental illness. "Since few people have the external devices, there is no big incentive to develop applications for them," said Aditya Khosla, an MIT graduate student. "Since there are no applications, there's no incentive for people to buy the devices. We thought we should break this circle and try to make an eye tracker that works on a single mobile device, using just your front-facing camera," he said.

ABSTRACT Deep neural networks (DNNs) have been successfully applied to a wide variety of acoustic modeling tasks in recent years. These include the applications of DNNs either in a discriminative feature extraction or in a hybrid acoustic modeling scenario. Despite the rapid progress in this area, a number of challenges remain in training DNNs. This paper presents an effective way of training DNNs using a manifold learning based regularization framework. In this framework, the parameters of the network are optimized to preserve underlying manifold based relationships between speech feature vectors while minimizing a measure of loss between network outputs and targets. This is achieved by incorporating manifold based locality constraints in the objective criterion of DNNs. Empirical evidence is provided to demonstrate that training a network with manifold constraints preserves structural compactness in the hidden layers of the network. Manifold regularization is applied to train bottleneck DNNs for feature extraction in hidden Markov model (HMM) based speech recognition. The experiments in this work are conducted on the Aurora-2 spoken digits and the Aurora-4 read news large vocabulary continuous speech recognition tasks. The performance is measured in terms of word error rate (WER) on these tasks. It is shown that the manifold regularized DNNs result in up to 37% reduction in WER relative to standard DNNs. Index Terms-- manifold learning, deep neural networks, manifold regularization, manifold regularized deep neural networks, speech recognition 1. INTRODUCTION Recently there has been a resurgence of research in the area of deep neural networks (DNNs) for acoustic modeling in automatic speech recognition (ASR) [1-6]. Much of this research has been concentrated on techniques for regularization of the algorithms used for DNN parameter estimation [7-9]. At the same time, there has also been a great deal of research on graph based techniques that facilitate the preservation of local neighborhood relationships among feature vectors for parameter estimation in a number of application areas [10-13]. Algorithms that preserve these local relationships are often referred to as having the effect of applying manifold based constraints.

Providing a unique approach to machine learning, this text contains fresh and intuitive, yet rigorous, descriptions of all fundamental concepts necessary to conduct research, build products, tinker, and play. By prioritizing geometric intuition, algorithmic thinking, and practical real world applications in disciplines including computer vision, natural language processing, economics, neuroscience, recommender systems, physics, and biology, this text provides readers with both a lucid understanding of foundational material as well as the practical tools needed to solve real-world problems. With in-depth Python and MATLAB/OCTAVE-based computational exercises and a complete treatment of cutting edge numerical optimization techniques, this is an essential resource for students and an ideal reference for researchers and practitioners working in machine learning, computer science, electrical engineering, signal processing, and numerical optimization.

Scientists, including one of Indian-origin, have developed a new artificial intelligence software that can turn any smartphone into an eye-tracking device. Eye-tracking technology - which can determine where in a visual scene people are directing their gaze - has been widely used in psychological experiments and marketing research, but the required pricey hardware has kept it from finding consumer applications. In addition to making existing applications of eye-tracking technology more accessible, the system developed by researchers at Massachusetts Institute of Technology (MIT) and University of Georgia may enable new computer interfaces or help detect signs of incipient neurological disease or mental illness. "Since few people have the external devices, there is no big incentive to develop applications for them," said Aditya Khosla, an MIT graduate student. "Since there are no applications, there's no incentive for people to buy the devices. We thought we should break this circle and try to make an eye tracker that works on a single mobile device, using just your front-facing camera," he said.

Student developers at the Apple Worldwide Developer's conference say they're ready to bring Siri to the masses, and make the personal digital assistant more useful. SAN FRANCISCO - What are the greatest, state-of-the-art apps for Apple iPhones, iPads, TVs and the Watch? Apple this week handed out awards to 12 app makers who are stretching the boundaries in what the company calls its Design Awards. The nods are given to put a spotlight on the best and brightest in app world. We sat down with most of the winners for an extended podcast at Apple's Worldwide Developer Conference (WWDC) here to talk about their apps, the state of the app world and their take on new app features that Apple introduced at WWDC.

Boston: Scientists, including one of Indian-origin, have developed a new artificial intelligence software that can turn any smartphone into an eye-tracking device. Eye-tracking technology - which can determine where in a visual scene people are directing their gaze - has been widely used in psychological experiments and marketing research, but the required pricey hardware has kept it from finding consumer applications. In addition to making existing applications of eye-tracking technology more accessible, the system developed by researchers at Massachusetts Institute of Technology (MIT) and University of Georgia may enable new computer interfaces or help detect signs of incipient neurological disease or mental illness. "Since few people have the external devices, there is no big incentive to develop applications for them," said Aditya Khosla, an MIT graduate student. "Since there are no applications, there's no incentive for people to buy the devices. We thought we should break this circle and try to make an eye tracker that works on a single mobile device, using just your front-facing camera," he said.

SAN FRANCISCO - SEPTEMBER 08: Google Vice President of Search Product and User Experience Marissa Mayer speaks during an announcement September 8, 2010 in San Francisco, California. Google announced the launch of Google Instant, a faster version of Google search that streams results live as you type your query. Google is consistently exploring all facets of virtual learning with the success of online applications, with a new artificial intelligence lab. Focusing on machines learning for the advancement of its products, Google Research Europe would be based in Switzerland. Following Google's recently launched Assistant, the company's European research team on artificial intelligence would be under the expertise of Emmanuel Mogenet plus up to a few hundred colleagues.

"There are worse crimes than burning books. One of them is not reading them,"Joseph Brodsky, a Russian and American poet, once said. Books let the reader experience new, different worlds, unexpected events, wild adventures. But foremost, they open the access to the minds of others, minds of characters and minds of narrators. Common sense tells us that reading fiction should train people in understanding what others think and feel.

Recently I outlined a short series of posts I'll be writing about how I landed a job in autonomous vehicles. My background is that I have a pretty solid foundation in software engineering, including an undergraduate degree in computer science. But most recently my programming has been on the web, not so much in the machine learning and embedded systems areas that dominate vehicle software. Artificial Intelligence for Robotics (Udacity): This is a terrific and super-fun introduction into self-driving cars by Sebastian Thrun. Thrun is both the founder of Udacity and also the founder of Google's self-driving car project and also a former professor at Stanford. Taking the class is like being in the presence of greatness.