We study the problem of meta-learning through the lens of online convex optimization, developing a meta-algorithm bridging the gap between popular gradient-based meta-learning and classical regularization-based multi-task transfer methods. Our method is the first to simultaneously satisfy good sample efficiency guarantees in the convex setting, with generalization bounds that improve with task-similarity, while also being computationally scalable to modern deep learning architectures and the many-task setting. Despite its simplicity, the algorithm matches, up to a constant factor, a lower bound on the performance of any such parameter-transfer method under natural task similarity assumptions. We use experiments in both convex and deep learning settings to verify and demonstrate the applicability of our theory.

We aim to design adaptive online learning algorithms that take advantage of any special structure that might be present in the learning task at hand, with as little manual tuning by the user as possible. A fundamental obstacle that comes up in the design of such adaptive algorithms is to calibrate a so-called step-size or learning rate hyperparameter depending on variance, gradient norms, etc. A recent technique promises to overcome this difficulty by maintaining multiple learning rates in parallel. This technique has been applied in the MetaGrad algorithm for online convex optimization and the Squint algorithm for prediction with expert advice. However, in both cases the user still has to provide in advance a Lipschitz hyperparameter that bounds the norm of the gradients. Although this hyperparameter is typically not available in advance, tuning it correctly is crucial: if it is set too small, the methods may fail completely; but if it is taken too large, performance deteriorates significantly. In the present work we remove this Lipschitz hyperparameter by designing new versions of MetaGrad and Squint that adapt to its optimal value automatically. We achieve this by dynamically updating the set of active learning rates. For MetaGrad, we further improve the computational efficiency of handling constraints on the domain of prediction, and we remove the need to specify the number of rounds in advance.

Cluster analysis is a staple of unsupervised machine learning and data science. It is very useful for data mining and big data because it automatically finds patterns in the data, without the need for labels, unlike supervised machine learning. In a real-world environment, you can imagine that a robot or an artificial intelligence won't always have access to the optimal answer, or maybe there isn't an optimal correct answer. You'd want that robot to be able to explore the world on its own, and learn things just by looking for patterns. In this course we are first going to talk about clustering.

It shouldn't just fall on businesses to address the talent shortage issue – universities have a role to play too. It is encouraging to see that universities are adding more machine learning and data science courses every day, with some making these new disciplines part of core curricula for certain degrees. But it shouldn't stop there – while academia provides students with theoretical training, enterprises can provide insight and experience based on real-world business problems. Businesses should step in by working with universities to help students gain practical, on-the-job experience. One way of doing this is to make work experience a course requirement. Progressive universities make it compulsory for students taking these courses to spend a semester working for a company in a relevant field.

Any job opening in a major organization typically invites hundreds of applications; yet only 10 percent of the incoming resumes are relevant! Imagine placing a job advertisement in a newspaper and bracing for the deluge of applications that would consume weeks of your time to sift through. This is how the process of recruitment was initiated in organizations across the world till a few years back. Thanks to the advent of artificial intelligence (AI) supported systems, this extremely cumbersome process is now taken over by softwares and search algorithms that are able to successfully prune out the few people matching your requirements from a pile of irrelevant applicants. This is just one manifestation of the way artificial intelligence is re-shaping and revolutionizing every sphere in our lives, including human resource management.

Learn Convolutional Neural Networks for Visual Recognition and the building blocks and methods associated with them. Deep Learning has made some huge and significant contributions and it's one of the mostly adopted techniques in order to drive insights from your data nowadays. Convolutional neural networks have gained a special status over the last few years as an especially promising form of deep learning. Rooted in image processing, convolutional layers have found their way into virtually all subfields of deep learning, and are very successful for the most part. Convolutional Neural Networks are very similar to ordinary Neural Networks: they are made up of neurons that have learnable weights and biases.

Education was traditionally seen as an enabler of social mobility. In other words, if you were from a low-income family, you could improve your financial and social standing by getting an education. And for a while, it worked, but inequality is on the rise again. These days, college and university degrees are, at least in developed countries, a dime a dozen and you need a postgraduate qualification to get an entry-level position. The advantage of education to boost social mobility is more noticeable in developing countries where the demand for highly educated individuals outstrips the supply.

I am incredibly grateful about how my academic year started so far: four preprints were at least conditionally accepted for publication in a forthcoming book on topological methods in data visualization, while another publication of my new lab was accepted as a poster for ICLR 2019. The underlying theme of all these publications is to shift the focus of machine learning towards topological methods, i.e. methods that focus on connectivity properties of input data. I am convinced that thinking about these types of properties is worthwhile, as the resulting shift in perspective often leads to novel insights. This spring of papers follows two themes: in the first, topology is used directly to drive algorithms, for example to classify data, or to elucidate its properties. In the second theme, topology is used indirectly to learn something about the behaviour of other algorithms. In Persistent Intersection Homology for the Analysis of Discrete Data, Markus Banagl, Filip Sadlo, Heike Leitte, and I describe how to use persistent intersection homology, an extension of persistent homology in order to describe spaces that do not consist of a single manifold, but of multiple ones.

In this book, the first four chapters are provided as a guide for teachers who want to use the book for teacher training and development. Using the tools, tips and activities provided in these first chapters a teacher with some basic experience of using technology in the classroom should be able to create motivating hands-on edtech training for their peers or for pre-service trainee teachers.

It is no doubt a sign of progress that a significant proportion of organizations and managers today appear to feel guilty when they admit that they are making big management decisions in an intuitive rather than evidence-based way. Indeed, being data-driven has joined the ranks of "innovative", "diverse", and "socially responsible" as the one of most laudable features of organizational culture, at least if we go by company websites. Although feeling the pressure to demonstrate that objective facts -- instead of subjective preferences -- underlie managers' key choices is no doubt a major step towards actually becoming a data-driven organization, it's an ambitious goal for any company, requiring a big cultural transformation, which will need to transcend the wishes of senior leaders to create real changes in how people think, feel, and act at all levels of the organization. And, as with any cultural transformation, managers are a critical agent of change. As organization turbocharge their ability to gather more and more data -- and it's not so much about size, but rather about quality -- what matters most is having people who can ask the right questions to the data.