We consider high-dimensional distribution estimation through autoregressive networks. By combining the concepts of sparsity, mixtures and parameter sharing we obtain a simple model which is fast to train and which achieves state-of-the-art or better results on several standard benchmark datasets. Specifically, we use an L1-penalty to regularize the conditional distributions and introduce a procedure for automatic parameter sharing between mixture components. Moreover, we propose a simple distributed representation which permits exact likelihood evaluations since the latent variables are interleaved with the observable variables and can be easily integrated out. Our model achieves excellent generalization performance and scales well to extremely high dimensions.

Structured prediction is used in areas such as computer vision and natural language processing to predict structured outputs such as segmentations or parse trees. In these settings, prediction is performed by MAP inference or, equivalently, by solving an integer linear program. Because of the complex scoring functions required to obtain accurate predictions, both learning and inference typically require the use of approximate solvers. We propose a theoretical explanation to the striking observation that approximations based on linear programming (LP) relaxations are often tight on real-world instances. In particular, we show that learning with LP relaxed inference encourages integrality of training instances, and that tightness generalizes from train to test data.

Perhaps the most important news of our day is that datasets--not algorithms--might be the key limiting factor to development of human-level artificial intelligence. At the dawn of the field of artificial intelligence, in 1967, two of its founders famously anticipated that solving the problem of computer vision would take only a summer. Now, almost a half century later, machine learning software finally appears poised to achieve human-level performance on vision tasks and a variety of other grand challenges. What took the AI revolution so long? A review of the timing of the most publicized AI advances over the past thirty years suggests a provocative explanation: perhaps many major AI breakthroughs have actually been constrained by the availability of high-quality training datasets, and not by algorithmic advances.

We propose to model the fixation locations of the human eye when observing a still image by a Markovian point process in R 2 . Our approach is data driven using k-means clustering of the fixation locations to identify distinct salient regions of the image, which in turn correspond to the states of our Markov chain. Bayes factors are computed as model selection criterion to determine the number of clusters. Furthermore, we demonstrate that the behaviour of the human eye differs from this model when colour information is removed from the given image.

What a wonderful treasure trove this paper is! Schmidhuber provides all the background you need to gain an overview of deep learning (as of 2014) and how we got there through the preceding decades. Starting from recent DL results, I tried to trace back the origins of relevant ideas through the past half century and beyond. The main part of the paper runs to 35 pages, and then there are 53 pages of references. Now, I know that many of you think I read a lot of papers – just over 200 a year on this blog – but if I did nothing but review these key works in the development of deep learning it would take me about 4.5 years to get through them at that rate! And when I'd finished I'd still be about 6 years behind the then current state of the art!

The official title of this free book available in PDF format is Machine Learning Cheat Sheet. See table of content screenshot below. The chapters 17 to 28 (the most interesting ones in my opinion) seem like a work in progress - I'm sure the authors intend to make them a bit bigger. For a more modern and applied book, get Dr Granville's book on data science.

Probabilistic models with weighted formulas, known as Markov models or log-linear models, are used in many domains. Recent models of weighted orderings between elements that have been proposed as flexible tools to express preferences under uncertainty, are also potentially useful in applications like planning, temporal reasoning, and user modeling. Their computational properties are very different from those of conventional Markov models; because of the transitivity of the “less than” relation, standard methods that exploit structure of the models, such as variable elimination, are not directly applicable, as there are no conditional independencies between the orderings within connected components. The best known algorithms for general inference inthese models are exponential in the number of statements. Here, we present the first algorithms that exploit the available structure. We begin with the special case of models in the form of chains; we present an exact O(n^3) algorithm, where n is the total number of elements. Next, we generalize this technique to models in which the set of statements are comprised of arbitrary sets of atomic weighted preference formulas (while the query and evidence are conjunctions of atomic preference formulas), and the resulting exact algorithm runs in time O(m * n^2 * n^c), where m is the number of preference formulas, n is the number of elements, and c is the maximum number of elements in a linear cut (which depends both on the structure of the model and the order in which the elements are processed)—therefore, this algorithm is tractable for cases in which c can be bounded to a low value. Finally, we report on the results of an empirical evaluation of both algorithms, showing how they scale with reasonably-sized models.

We introduce the concept of weighted rules under the stable model semantics following the log-linear models of Markov Logic. This provides versatile methods to overcome the deterministic nature of the stable model semantics, such as resolving inconsistencies in answer set programs, ranking stable models, associating probability to stable models, and applying statistical inference to computing weighted stable models. We also present formal comparisons with related formalisms, such as answer set programs, Markov Logic, ProbLog, and P-log.

Human mobility modeling for either transportation system development or individual location based services has a tangible impact on people's everyday experience. In recent years cell phone data has received a lot of attention as a promising data source because of the wide coverage, long observation period, and low cost. The challenge in utilizing such data is how to robustly extract people's trip sequences from sparse and noisy cell phone data and endow the extracted trips with semantic meaning, i.e., trip purposes.In this study we reconstruct trip sequences from sparse cell phone records. Next we propose a Bayesian trip purpose classification method and compare it to a Markov random field based trip purpose clustering method, representing scenarios with and without labeled training data respectively. This procedure shows how the cell phone data, despite their coarse granularity and sparsity, can be turned into a low cost, long term, and ubiquitous sensor network for mobility related services.

We cast the Proactive Learning (PAL) problem—Active Learning (AL) with multiple reluctant, fallible, cost-varying oracles—as a Partially Observable Markov Decision Process (POMDP). The agent selects an oracle at each time step to label a data point, while it maintains a belief over the true underlying correctness of its current dataset’s labels. The goal is to minimize labeling costs while considering the value of obtaining correct labels, thus maximizing final resultant classifier accuracy. We prove three properties that show our particular formulation leads to a structured and bounded-size set of belief points, enabling strong performance of point-based methods to solve the POMDP. Our method is compared with the original three algorithms proposed by Donmez and Carbonell and a simple baseline. We demonstrate that our approach matches or improves upon the original approach within five different oracle scenarios, each on two datasets. Finally, our algorithm provides a general, well-defined mathematical foundation to build upon.