Data and knowledge representation are fundamental concepts in machine learning. The quality of the representation impacts the performance of the learning model directly. Feature learning transforms or enhances raw data to structures that are effectively exploited by those models. In recent years, several works have been using complex networks for data representation and analysis. However, no feature learning method has been proposed for such category of techniques. Here, we present an unsupervised feature learning mechanism that works on datasets with binary features. First, the dataset is mapped into a feature--sample network. Then, a multi-objective optimization process selects a set of new vertices to produce an enhanced version of the network. The new features depend on a nonlinear function of a combination of preexisting features. Effectively, the process projects the input data into a higher-dimensional space. To solve the optimization problem, we design two metaheuristics based on the lexicographic genetic algorithm and the improved strength Pareto evolutionary algorithm (SPEA2). We show that the enhanced network contains more information and can be exploited to improve the performance of machine learning methods. The advantages and disadvantages of each optimization strategy are discussed.

In this work we introduce malware detection from raw byte sequences as a fruitful research area to the larger machine learning community. Building a neural network for such a problem presents a number of interesting challenges that have not occurred in tasks such as image processing or NLP. In particular, we note that detection from raw bytes presents a sequence problem with over two million time steps and a problem where batch normalization appear to hinder the learning process. We present our initial work in building a solution to tackle this problem, which has linear complexity dependence on the sequence length, and allows for interpretable sub-regions of the binary to be identified. In doing so we will discuss the many challenges in building a neural network to process data at this scale, and the methods we used to work around them.

The original problem of supervised classification considers the task of automatically assigning objects to their respective classes on the basis of numerical measurements derived from these objects. Classifiers are the tools that implement the actual functional mapping from these measurements---also called features or inputs---to the so-called class label---or output. The fields of pattern recognition and machine learning study ways of constructing such classifiers. The main idea behind supervised methods is that of learning from examples: given a number of example input-output relations, to what extent can the general mapping be learned that takes any new and unseen feature vector to its correct class? This chapter provides a basic introduction to the underlying ideas of how to come to a supervised classification problem. In addition, it provides an overview of some specific classification techniques, delves into the issues of object representation and classifier evaluation, and (very) briefly covers some variations on the basic supervised classification task that may also be of interest to the practitioner.

Machine learning is the hottest tech trend these days and it's showing up in all sorts of places in tech. Although it is deemed a high-security risk, many companies feel the pressure to invest in such a strategy (before fully understanding what they are aiming to achieve). Service management software provider ServiceNow Inc. has surveyed 500 CIOs and has concluded that "many businesses are preparing for the widespread adoption of machine learning to automate decision-making." This survey explores the strategies CIOs are adopting to realize value from machine learning and the competitive advantage for organizations that are advancing to decision automation. Almost 90 percent of the CIOs surveyed said that greater automation will increase the accuracy and speed of decisions and over half of them said that machine learning is one of the focus of their digitization efforts.

Deep learning is having a large impact on the field of natural language processing. But, as a beginner, where do you start? Both deep learning and natural language processing are huge fields. What are the salient aspects of each field to focus on and which areas of NLP is deep learning having the most impact? In this post, you will discover a primer on deep learning for natural language processing.

The word2vec method based on skip-gram with negative sampling (Mikolov et al., 2013) [49] was published in 2013 and had a large impact on the field, mainly through its accompanying software package, which enabled efficient training of dense word representations and a straightforward integration into downstream models. In some respects, we have come far since then: Word embeddings have established themselves as an integral part of Natural Language Processing (NLP) models. In other aspects, we might as well be in 2013 as we have not found ways to pre-train word embeddings that have managed to supersede the original word2vec. This post will focus on the deficiencies of word embeddings and how recent approaches have tried to resolve them. If not otherwise stated, this post discusses pre-trained word embeddings, i.e. word representations that have been learned on a large corpus using word2vec and its variants.

In this semi-tutorial paper, we first review the information-theoretic approach to account for the computational costs incurred during the search for optimal actions in a sequential decision-making problem. The traditional (MDP) framework ignores computational limitations while searching for optimal policies, essentially assuming that the acting agent is perfectly rational and aims for exact optimality. Using the free-energy, a variational principle is introduced that accounts not only for the value of a policy alone, but also considers the cost of finding this optimal policy. The solution of the variational equations arising from this formulation can be obtained using familiar Bellman-like value iterations from dynamic programming (DP) and the Blahut-Arimoto (BA) algorithm from rate distortion theory. Finally, we demonstrate the utility of the approach for generating hierarchies of state abstractions that can be used to best exploit the available computational resources.

We could say our 30th annual list of the most transformative products and discoveries required trucks full of experts, hours of toil, and countless friendship-ending debates. That's true, but you just want the good stuff. A robot just made me french fries. Delicious, they cooked for four minutes less than the instructions dictated. One minute less, they'd've been soggy.

A survey of 500 chief information officers (CIOs) from around the world by ServiceNow has found that machine learning has arrived in the enterprise, and is making material contributions to everyday work. To realise its full value, technology leaders must find skilled talent to work side-by-side with machines, in addition to redesigning their organisations and processes. CIOs were interviewed in 11 countries across 25 industries, including 46 CIOs in the UK, to uncover the competitive benefits of adopting machine learning and hear how those leaders are driving results. See also: Government CIO I.T. budget breakdown: Gartner IDC estimates that investment in machine learning will nearly double by 2020, and recent analysis shows that machine learning specialists are among the fast-growing roles in IT. Humans are working side-by-side with smart machines for better accuracy, speed and growth of business.

Intelligent machines have learned to read and write, recognize images, and predict dangerous mutations. But how does a machine learn to learn in the first place? The art of'learning to learn' (or meta-learning) is now widely recognized as a cornerstone of artificial intelligence research. Over the last few years, the idea of using data to learn the learning algorithms has gained momentum -- and massive computational resources and datasets have made it possible. In 2016, Nando de Freitas, a Senior Fellow in CIFAR's Learning in Machines & Brains program, demonstrated a novel approach to learning to learn.