Artificial intelligence (AI), deep learning, and neural networks represent incredibly exciting and powerful machine learning-based techniques used to solve many real-world problems. For a primer on machine learning, you may want to read this five-part series that I wrote. While human-like deductive reasoning, inference, and decision-making by a computer is still a long time away, there have been remarkable gains in the application of AI techniques and associated algorithms. The concepts discussed here are extremely technical, complex, and based on mathematics, statistics, probability theory, physics, signal processing, machine learning, computer science, psychology, linguistics, and neuroscience. That said, this article is not meant to provide such a technical treatment, but rather to explain these concepts at a level that can be understood by most non-practitioners, and can also serve as a reference or review for technical folks as well.

Analyzing the temporal behavior of nodes in time-varying graphs is useful for many applications such as targeted advertising, community evolution and outlier detection. In this paper, we present a novel approach, STWalk, for learning trajectory representations of nodes in temporal graphs. The proposed framework makes use of structural properties of graphs at current and previous time-steps to learn effective node trajectory representations. STWalk performs random walks on a graph at a given time step (called space-walk) as well as on graphs from past time-steps (called time-walk) to capture the spatio-temporal behavior of nodes. We propose two variants of STWalk to learn trajectory representations. In one algorithm, we perform space-walk and time-walk as part of a single step. In the other variant, we perform space-walk and time-walk separately and combine the learned representations to get the final trajectory embedding. Extensive experiments on three real-world temporal graph datasets validate the effectiveness of the learned representations when compared to three baseline methods. We also show the goodness of the learned trajectory embeddings for change point detection, as well as demonstrate that arithmetic operations on these trajectory representations yield interesting and interpretable results.

Approximately 658 corporate decision makers have been surveyed for their confidence in their own decision-making skills and their acceptance of the importance of Artificial Intelligence (A.I.) in general as well as in augmenting (or replacing) their decision making. Furthermore, the survey reveals the general perception of the corporate data-driven environment available to decision maker, e.g., the structure and perceived quality of available data. A comprehensive overview and analysis of our AI sentiments as it relates to corporate decision making is provided as a function Gender, Age, Job-level, Work area and Education. You don't need to make an effort to find articles, blogs, social media postings, books and insights in general on how Artificial Intelligence (hereafter abbreviated A.I.) will provide wonders for all human beings, society and leapfrog corporate efficiencies and shareholder values for the ones adapting to A.I. (of which you would be pretty silly not too of course).

AI is a booming industry with a lot of noise, thought leadership, and hype. However, as we attend industry events, work with clients, and tell the story of AI for customer data, there's one common trend. Many of the people we talk to only have a loose idea of what AI does, with little or no mind to what it is. This post will serve as an easy to read primer on what AI truly is, and what kinds of AI are being developed/where things stand today in the ecosystem. AI is a form of intelligence - Specifically AI is a synthetic intelligence - intelligence of a man-made yet real quality.

We review the problem of defining and inferring a "state" for a control system based on complex, high-dimensional, highly uncertain measurement streams such as videos. Such a state, or representation, should contain all and only the information needed for control, and discount nuisance variability in the data. It should also have finite complexity, ideally modulated depending on available resources. This representation is what we want to store in memory in lieu of the data, as it "separates" the control task from the measurement process. For the trivial case with no dynamics, a representation can be inferred by minimizing the Information Bottleneck Lagrangian in a function class realized by deep neural networks. The resulting representation has much higher dimension than the data, already in the millions, but it is smaller in the sense of information content, retaining only what is needed for the task. This process also yields representations that are invariant to nuisance factors and having maximally independent components. We extend these ideas to the dynamic case, where the representation is the posterior density of the task variable given the measurements up to the current time, which is in general much simpler than the prediction density maintained by the classical Bayesian filter. Again this can be finitely-parametrized using a deep neural network, and already some applications are beginning to emerge. No explicit assumption of Markovianity is needed; instead, complexity trades off approximation of an optimal representation, including the degree of Markovianity.

Artificial Intelligence (AI) is considered to be the next stupendous technological development, alike past developments such as the revolution of industries, the computer era, and the emergence of smartphone technology. Advances in image and voice recognition are driving the growth of the artificial intelligence market as improved image recognition technology is critical to offer enhanced drones, self-driving cars, and robotics. The AI market can be categorized based on solutions, technologies, end use, and geography. The two major factors enabling market growth are emerging AI technologies and growth in big data espousal. The growing prominence of artificial intelligence is enabling new players to venture into the market by offering niche application-specific solutions.

We study a variant of the stochastic multi-armed bandit (MAB) problem in which the rewards are corrupted. In this framework, motivated by privacy preservation in online recommender systems, the goal is to maximize the sum of the (unobserved) rewards, based on the observation of transformation of these rewards through a stochastic corruption process with known parameters. We provide a lower bound on the expected regret of any bandit algorithm in this corrupted setting. We devise a frequentist algorithm, KLUCB-CF, and a Bayesian algorithm, TS-CF and give upper bounds on their regret. We also provide the appropriate corruption parameters to guarantee a desired level of local privacy and analyze how this impacts the regret. Finally, we present some experimental results that confirm our analysis.

Regularization is one of the crucial ingredients of deep learning, yet the term regularization has various definitions, and regularization methods are often studied separately from each other. In our work we present a systematic, unifying taxonomy to categorize existing methods. We distinguish methods that affect data, network architectures, error terms, regularization terms, and optimization procedures. We do not provide all details about the listed methods; instead, we present an overview of how the methods can be sorted into meaningful categories and sub-categories. This helps revealing links and fundamental similarities between them. Finally, we include practical recommendations both for users and for developers of new regularization methods.

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.