Build real-world Artificial Intelligence (AI) applications to intelligently interact with the world around you, explore real-world scenarios, and learn about the various algorithms that can be used to build AI applications. Packed with insightful examples and topics such as predictive analytics and deep learning, this course is a must-have for Python developers. Prateek Joshi is an artificial intelligence researcher, published author of five books, and TEDx speaker. He is the founder of Pluto AI, a venture-funded Silicon Valley start-up that builds analytics platforms for smart water management powered by deep learning. His work in this field has led to patents, tech demos, and research papers at major IEEE conferences.

There's often a fine line between hero and villain, and by most accounts, artificial intelligence (AI) is on the villain side, sucking jobs out of the economy. These days you can't throw a rock without hitting some pundit prognosticating on the millions of jobs that will be lost from AI. One oft-cited Oxford University study predicted 47% of jobs are in jeopardy. But while AI conjures up robots and dystopian science fiction movies, it isn't magic. Today's AI consists of algorithms developed with "training data" that improve over time, otherwise known as machine learning.

About this course: An increasing volume of data is becoming available in biomedicine and healthcare, from genomic data, to electronic patient records and data collected by wearable devices. Recent advances in data science are transforming the life sciences, leading to precision medicine and stratified healthcare. In this course, you will learn about some of the different types of data and computational methods involved in stratified healthcare and precision medicine. You will have a hands-on experience of working with such data. And you will learn from leaders in the field about successful case studies.

Machine learning is an application of artificial intelligence. It provides the system an ability to automatically learn and to improve from experience without being thoroughly programmed. The primary aim of this is to allow the computers to learn automatically without human intervention. Google is one of the major advocates of this artificial intelligence. That is the reason behind making'Google Machine Learning Crash Course' available to millions of Googlers all around the world for free as part of Google AI initiative.

Al Olama said, "Academic institutions in the UAE play a key role in developing educational and training programmes and introducing disciplines that prepare the next generation of leaders who are capable of developing key sector." The Minister of State for AI commended the initiatives of academic institutions in the UAE to develop their educational curricula. He praised HCT's initiative to launch this specialised programme in AI science and technologies. Dr Al Shamsi highlighted the importance of cooperating with Oracle, the global organisation specialised in modern technologies, especially AI. Over the past years, HCT have worked closely with Oracle in technology education.

Frank-Wolfe algorithm (FW) and its variants have gained a surge of interests in machine learning community due to its projection-free property. Recently people have reduced the gradient evaluation complexity of FW algorithm to $\log(\frac{1}{\epsilon})$ for the smooth and strongly convex objective. This complexity result is especially significant in learning problem, as the overwhelming data size makes a single evluation of gradient computational expensive. However, in high-dimensional statistical estimation problems, the objective is typically not strongly convex, and sometimes even non-convex. In this paper, we extend the state-of-the-art FW type algorithms for the large-scale, high-dimensional estimation problem. We show that as long as the objective satisfies {\em restricted strong convexity}, and we are not optimizing over statistical limit of the model, the $\log(\frac{1}{\epsilon})$ gradient evaluation complexity could still be attained.

We introduce the Kronecker factored online Laplace approximation for overcoming catastrophic forgetting in neural networks. The method is grounded in a Bayesian online learning framework, where we recursively approximate the posterior after every task with a Gaussian, leading to a quadratic penalty on changes to the weights. The Laplace approximation requires calculating the Hessian around a mode, which is typically intractable for modern architectures. In order to make our method scalable, we leverage recent block-diagonal Kronecker factored approximations to the curvature. Our algorithm achieves over 90% test accuracy across a sequence of 50 instantiations of the permuted MNIST dataset, substantially outperforming related methods for overcoming catastrophic forgetting.

The central problem of this paper is the cost-sensitive binary classification problem, where different costs are associated with different types of mistakes. Several important machine learning applications such as medical decision making, targeted marketing, and intrusion detection can be naturally formalized as costsensitive classification setup ([1]). In these domains, the cost of missing a target is much higher than that of a false-positive, and classifiers that do not take misclassification costs into account do not perform well. The cost-sensitive classification problem has been extensively studied, and people have developed efficient algorithms with provable guarantees on the (generalization) error [6, 9, 26, 27, 11, 4]. These methods primarily take existing classification methods based on empirical risk minimization and try to adapt them in various ways to be sensitive to these misclassification costs. Despite all these efforts, the understanding of the fundamental limits of this problem is still missing. In this paper, we study the hardness of this problem by obtaining minimax lower bounds. In particular, we are interested in understanding how the cost parameter influences the hardness or complexity of the cost-sensitive classification. Minimax Lower Bounds Understanding the hardness or fundamental limits of a learning problem is important for practice for the following reasons: - They give an estimate on the number of samples required for a good performance of a learning algorithm.

Inverse reinforcement learning (IRL) is the problem of learning the preferences of an agent from the observations of its behavior on a task. While this problem has been well investigated, the related problem of {\em online} IRL---where the observations are incrementally accrued, yet the demands of the application often prohibit a full rerun of an IRL method---has received relatively less attention. We introduce the first formal framework for online IRL, called incremental IRL (I2RL), and a new method that advances maximum entropy IRL with hidden variables, to this setting. Our formal analysis shows that the new method has a monotonically improving performance with more demonstration data, as well as probabilistically bounded error, both under full and partial observability. Experiments in a simulated robotic application of penetrating a continuous patrol under occlusion shows the relatively improved performance and speed up of the new method and validates the utility of online IRL.

Radio Frequency Identification technology has gained popularity for cheap and easy deployment. In the realm of manufacturing shopfloor, it can be used to track the location of manufacturing objects to achieve better efficiency. The underlying challenge of localization lies in the non-stationary characteristics of manufacturing shopfloor which calls for an adaptive life-long learning strategy in order to arrive at accurate localization results. This paper presents an evolving model based on a novel evolving intelligent system, namely evolving Type-2 Quantum Fuzzy Neural Network (eT2QFNN), which features an interval type-2 quantum fuzzy set with uncertain jump positions. The quantum fuzzy set possesses a graded membership degree which enables better identification of overlaps between classes. The eT2QFNN works fully in the evolving mode where all parameters including the number of rules are automatically adjusted and generated on the fly. The parameter adjustment scenario relies on decoupled extended Kalman filter method. Our numerical study shows that eT2QFNN is able to deliver comparable accuracy compared to state-of-the-art algorithms.