Department of Informatics, King's College London; osvaldo.simeone@kcl.ac.uk ABSTRACT This monograph aims at providing an introduction to key concepts, algorithms, and theoretical frameworks in machine learning, including supervised and unsupervised learning, statistical learning theory, probabilistic graphical models and approximate inference. The intended readership consists of electrical engineers with a background in probability and linear algebra. The treatment builds on first principles, and organizes the main ideas according to clearly defined categories, such as discriminative and generative models, frequentist and Bayesian approaches, exact and approximate inference, directed and undirected models, and convex and non-convex optimization. The mathematical framework uses information-theoretic measures as a unifying tool. The text offers simple and reproducible numerical examples providing insights into key motivations and conclusions. Rather than providing exhaustive details on the existing myriad solutions in each specific category, for which the reader is referred to textbooks and papers, this monograph is meant as an entry point for an engineer into the literature on machine learning.

Crowdsourcing has been successfully applied in many domains including astronomy, cryptography and biology. In order to test its potential for useful application in a Smart Grid context, this paper investigates the extent to which a crowd can contribute predictive hypotheses to a model of residential electric energy consumption. In this experiment, the crowd generated hypotheses about factors that make one home different from another in terms of monthly energy usage. To implement this concept, we deployed a web-based system within which 627 residential electricity customers posed 632 questions that they thought predictive of energy usage. While this occurred, the same group provided 110,573 answers to these questions as they accumulated. Thus users both suggested the hypotheses that drive a predictive model and provided the data upon which the model is built. We used the resulting question and answer data to build a predictive model of monthly electric energy consumption, using random forest regression. Because of the sparse nature of the answer data, careful statistical work was needed to ensure that these models are valid. The results indicate that the crowd can generate useful hypotheses, despite the sparse nature of the dataset.

This paper introduces a novel approach to texture synthesis based on generative adversarial networks (GAN) (Goodfellow et al., 2014). We extend the structure of the input noise distribution by constructing tensors with different types of dimensions. We call this technique Periodic Spatial GAN (PSGAN). The PSGAN has several novel abilities which surpass the current state of the art in texture synthesis. First, we can learn multiple textures from datasets of one or more complex large images. Second, we show that the image generation with PSGANs has properties of a texture manifold: we can smoothly interpolate between samples in the structured noise space and generate novel samples, which lie perceptually between the textures of the original dataset. In addition, we can also accurately learn periodical textures. We make multiple experiments which show that PSGANs can flexibly handle diverse texture and image data sources. Our method is highly scalable and it can generate output images of arbitrary large size.

Generative adversarial networks (GANs) [7] are a recent approach to train generative models of data, which have been shown to work particularly well on image data. In the current paper we introduce a new model for texture synthesis based on GAN learning. By extending the input noise distribution space from a single vector to a whole spatial tensor, we create an architecture with properties well suited to the task of texture synthesis, which we call spatial GAN (SGAN). To our knowledge, this is the first successful completely data-driven texture synthesis method based on GANs. Our method has the following features which make it a state of the art algorithm for texture synthesis: high image quality of the generated textures, very high scalability w.r.t. the output texture size, fast real-time forward generation, the ability to fuse multiple diverse source images in complex textures. To illustrate these capabilities we present multiple experiments with different classes of texture images and use cases. We also discuss some limitations of our method with respect to the types of texture images it can synthesize, and compare it to other neural techniques for texture generation.

Convolutional sparse representations are a form of sparse representation with a dictionary that has a structure that is equivalent to convolution with a set of linear filters. While effective algorithms have recently been developed for the convolutional sparse coding problem, the corresponding dictionary learning problem is substantially more challenging. Furthermore, although a number of different approaches have been proposed, the absence of thorough comparisons between them makes it difficult to determine which of them represents the current state of the art. The present work both addresses this deficiency and proposes some new approaches that outperform existing ones in certain contexts. A thorough set of performance comparisons indicates a very wide range of performance differences among the existing and proposed methods, and clearly identifies those that are the most effective.

Artificial intelligence can accurately predict whether people are gay or straight based on photos of their faces, according to new research suggesting that machines can have significantly better "gaydar" than humans. The study from Stanford University – which found that a computer algorithm could correctly distinguish between gay and straight men 81% of the time, and 74% for women – has raised questions about the biological origins of sexual orientation, the ethics of facial-detection technology and the potential for this kind of software to violate people's privacy or be abused for anti-LGBT purposes. The machine intelligence tested in the research, which was published in the Journal of Personality and Social Psychology and first reported in the Economist, was based on a sample of more than 35,000 facial images that men and women publicly posted on a US dating website. The researchers, Michal Kosinski and Yilun Wang, extracted features from the images using "deep neural networks", meaning a sophisticated mathematical system that learns to analyze visuals based on a large dataset. The research found that gay men and women tended to have "gender-atypical" features, expressions and "grooming styles", essentially meaning gay men appeared more feminine and visa versa.

Regulatory compliance has always been and will always be one of the top priorities and concerns of every financial institution (FI). Regulatory reforms following the global financial crisis of 2008 compelled FIs to make substantial investments in risk and compliance – both in terms of technology and headcount – to prevent and remediate regulatory issues. Despite their best efforts, FIs often find themselves falling short of regulatory obligations owing to highly manual processes and silo-based solutions which hinder transparency, efficiency and availability of fast and meaningful data. Non-compliance means being slapped with hefty penalties not to mention consequent reputational damage. Compliance processes today need to be backed up like never before by automation, artificial intelligence and big data – to name a few crucial technologies – to keep up with increasing regulation and stricter enforcement.

A team of international researchers is urging people to share their selfies in order to help teach computers how to read faces and identify people with rare diseases. The Minerva and Me project - being led by Oxford University with the help of international researchers like WA Health clinical genetist Gareth Baynam - is seeking to use technology to spot rare diseases faster and more accurately. The crowd-sourced research initiative wants to build a database of photographs so the researchers can develop facial recognition software using machine learning algorithms that can identify rare diseases. The software would be able to suggest a disease condition and prompt further tests that could be used to help settle on a diagnosis - potentially reducing the instances of incorrect diagnosis. "We think computers can be used to help diagnose individuals who have particular diseases. To do this we are training computers to look at photographs of peoples' faces to try to identify combinations of subtle changes that might together be indicators of a specific disease," the researchers say.

How did one Harley-Davidson dealership in New York City go from selling one or two bikes a week to selling 15 in a weekend? Owner Asaf Jacobi took a risk on Adgorithms' 'Albert', an artificial intelligence (AI) driven marketing platform that works across digital channels. The results saw the dealership increasing leads by 2930% by the third month and driving Jacobi to set up a new call centre to handle all the new business. Albert can learn as he does and is able to "identify the audiences most likely to convert, eliminate low-value audiences, apply insights gained from one channel to other channels", according to Harley-Davidson NYC. The AI works with campaign creative and KPIs provided by the brand to autonomously execute holistic digital ad and marketing campaigns.

Face recognition software can now see through your cunning disguise – even you are wearing a mask. Amarjot Singh at the University of Cambridge and his colleagues trained a machine learning algorithm to locate 14 key facial points. These are the points the human brain pays most attention to when we look at someone's face. The researchers then hand-labelled 2000 photos of people wearing hats, glasses, scarves and fake beards to indicate the location of those same key points, even if they couldn't be seen. The algorithm looked at a subset of these images to learn how the disguised faces corresponded with the undisguised faces. The system accurately identified people a wearing scarf 77 per cent of the time – a cap and scarf 69 per cent of the time and a cap, scarf and glasses 55 per cent of the time.