The predictive power of neural networks often costs model interpretability. Several techniques have been developed for explaining model outputs in terms of input features; however, it is difficult to translate such interpretations into actionable insight. Here, we propose a framework to analyze predictions in terms of the model's internal features by inspecting information flow through the network. Given a trained network and a test image, we select neurons by two metrics, both measured over a set of images created by perturbations to the input image: (1) magnitude of the correlation between the neuron activation and the network output and (2) precision of the neuron activation. We show that the former metric selects neurons that exert large influence over the network output while the latter metric selects neurons that activate on generalizable features. By comparing the sets of neurons selected by these two metrics, our framework suggests a way to investigate the internal attention mechanisms of convolutional neural networks.

A central problem in statistics is model selection, the choice between competing models of a stochastic process whose observables are corrupted by noise. In the information-based paradigm of inference, model selection is performed by estimating the predictive performance of the com- peting models. The candidate model with the best estimated predictive performance is selected. Information-based inference is dependent on the accuracy of the estimate of the predictive complexity, a measure of the flexibility of the model in fitting the data. A large-sample-size approximation for the performance is the Akaike Information Criterion (AIC). The AIC approximation fails in a wide range of important applications, either significantly under or over-estimating the complexity. We introduce an improved approximation for the complexity which we use to define a new information criterion: the frequentist information criterion (FIC). FIC extends the applicability of information-based infer- ence to the finite-sample-size regime of regular models and to singular models. We demonstrate the power of the approach in a number of example problems.

Sparse Subspace Clustering (SSC) is a state-of-the-art method for clustering high-dimensional data points lying in a union of low-dimensional subspaces. However, while $\ell_1$ optimization-based SSC algorithms suffer from high computational complexity, other variants of SSC, such as Orthogonal Matching Pursuit-based SSC (OMP-SSC), lose clustering accuracy in pursuit of improving time efficiency. In this letter, we propose a novel Active OMP-SSC, which improves clustering accuracy of OMP-SSC by adaptively updating data points and randomly dropping data points in the OMP process, while still enjoying the low computational complexity of greedy pursuit algorithms. We provide heuristic analysis of our approach, and explain how these two active steps achieve a better tradeoff between connectivity and separation. Numerical results on both synthetic data and real-world data validate our analyses and show the advantages of the proposed active algorithm.

This survey explores Procedural Content Generation via Machine Learning (PCGML), defined as the generation of game content using machine learning models trained on existing content. As the importance of PCG for game development increases, researchers explore new avenues for generating high-quality content with or without human involvement; this paper addresses the relatively new paradigm of using machine learning (in contrast with search-based, solver-based, and constructive methods). We focus on what is most often considered functional game content such as platformer levels, game maps, interactive fiction stories, and cards in collectible card games, as opposed to cosmetic content such as sprites and sound effects. In addition to using PCG for autonomous generation, co-creativity, mixed-initiative design, and compression, PCGML is suited for repair, critique, and content analysis because of its focus on modeling existing content. We discuss various data sources and representations that affect the resulting generated content. Multiple PCGML methods are covered, including neural networks, long short-term memory (LSTM) networks, autoencoders, and deep convolutional networks; Markov models, $n$-grams, and multi-dimensional Markov chains; clustering; and matrix factorization. Finally, we discuss open problems in the application of PCGML, including learning from small datasets, lack of training data, multi-layered learning, style-transfer, parameter tuning, and PCG as a game mechanic.

There's a popular perception out there that most people, particularly office workers, are concerned that artificial intelligence (AI) is coming for their jobs. After all, more and more simple tasks in the workplace have become automated -- from daily reminders to finding and editing electronic documents. But are the office workers themselves truly worried that robots will take away jobs? In our new report The Future of Work: More than a Machine, we surveyed more 4,000 office workers across the U.S., U.K., and Germany and asked them about how technology is changing their jobs, especially advanced technology like AI, and how confident they feel about keeping their jobs in the future. The study suggests that instead of being anxious about technology taking over their jobs, office workers are optimistic about how it can boost productivity and work for them.

About this course: This course will introduce the learner to text mining and text manipulation basics. The course begins with an understanding of how text is handled by python, the structure of text both to the machine and to humans, and an overview of the nltk framework for manipulating text. The second week focuses on common manipulation needs, including regular expressions (searching for text), cleaning text, and preparing text for use by machine learning processes. The third week will apply basic natural language processing methods to text, and demonstrate how text classification is accomplished. The final week will explore more advanced methods for detecting the topics in documents and grouping them by similarity (topic modelling).

About this course: Case Studies: Finding Similar Documents A reader is interested in a specific news article and you want to find similar articles to recommend. What is the right notion of similarity? Moreover, what if there are millions of other documents? Each time you want to a retrieve a new document, do you need to search through all other documents? How do you group similar documents together?

Want to use something more interpertable, something that trains faster and performs pretty much just as well as the old Logistic Regression or even Neural Networks? You should consider Decision Trees for classification and regression. Decision Trees and their extension Random Forests are robust and easy-to-interpret machine learning algorithms for Classification and Regression tasks. Decision Trees and Decision Tree Learning together comprise a simple and fast way of learning a function that maps data x to outputs y, where x can be a mix of categorical and numeric variables and y can be categorical for classification, or numeric for regression. Methods such as SVMs, Logistic Regression and Deep Neural Nets pretty much do the same thing.

Cybersecurity machine learning is growing in popularity, according to Jon Oltsik, an analyst with Enterprise Strategy Group Inc. in Milford, Mass. Oltsik attended the recent Black Hat conference, where technology vendors were abuzz with talk of cybersecurity machine learning. ESG research asked 412 respondents about their understanding of artificial intelligence (AI) and cybersecurity machine learning, which revealed that only 30% said they were very knowledgeable on the subject. Only 12% of respondents said their organizations had deployed these systems widely. According to Olstik, the cybersecurity industry sees an opportunity, because only 6% of respondents in surveys said their organizations were not considering AI or machine learning deployments.

About this course: Welcome to our course on Object Oriented Programming in Java using data visualization. People come to this course with many different goals -- and we are really excited to work with all of you! Some of you want to be professional software developers, others want to improve your programming skills to implement that cool personal project that you've been thinking about, while others of you might not yet know why you're here and are trying to figure out what this course is all about. This is an intermediate Java course. We recommend this course to learners who have previous experience in software development or a background in computer science.