Belief Propagation (BP) is a widely used approximation for exact probabilistic inference in graphical models, such as Markov Random Fields (MRFs). In graphs with cycles, however, no exact convergence guarantees for BP are known, in general. For the case when all edges in the MRF carry the same symmetric, doubly stochastic potential, recent works have proposed to approximate BP by linearizing the update equations around default values, which was shown to work well for the problem of node classification. The present paper generalizes all prior work and derives an approach that approximates loopy BP on any pairwise MRF with the problem of solving a linear equation system. This approach combines exact convergence guarantees and a fast matrix implementation with the ability to model heterogenous networks. Experiments on synthetic graphs with planted edge potentials show that the linearization has comparable labeling accuracy as BP for graphs with weak potentials, while speeding-up inference by orders of magnitude.

Many machine learning applications use latent variable models to explain structure in data, whereby visible variables (= coordinates of the given datapoint) are explained as a probabilistic function of some hidden variables. Finding parameters with the maximum likelihood is NP-hard even in very simple settings. In recent years, provably efficient algorithms were nevertheless developed for models with linear structures: topic models, mixture models, hidden markov models, etc. These algorithms use matrix or tensor decomposition, and make some reasonable assumptions about the parameters of the underlying model. But matrix or tensor decomposition seems of little use when the latent variable model has nonlinearities. The current paper shows how to make progress: tensor decomposition is applied for learning the single-layer {\em noisy or} network, which is a textbook example of a Bayes net, and used for example in the classic QMR-DT software for diagnosing which disease(s) a patient may have by observing the symptoms he/she exhibits. The technical novelty here, which should be useful in other settings in future, is analysis of tensor decomposition in presence of systematic error (i.e., where the noise/error is correlated with the signal, and doesn't decrease as number of samples goes to infinity). This requires rethinking all steps of tensor decomposition methods from the ground up. For simplicity our analysis is stated assuming that the network parameters were chosen from a probability distribution but the method seems more generally applicable.

Modeling continuous-time physiological processes that manifest a patient's evolving clinical states is a key step in approaching many problems in healthcare. In this paper, we develop the Hidden Absorbing Semi-Markov Model (HASMM): a versatile probabilistic model that is capable of capturing the modern electronic health record (EHR) data. Unlike existing models, the HASMM accommodates irregularly sampled, temporally correlated, and informatively censored physiological data, and can describe non-stationary clinical state transitions. Learning the HASMM parameters from the EHR data is achieved via a novel forward-filtering backward-sampling Monte-Carlo EM algorithm that exploits the knowledge of the endpoint clinical outcomes (informative censoring) in the EHR data, and implements the E-step by sequentially sampling the patients' clinical states in the reversetime direction while conditioning on the future states. Real-time inferences are drawn via a forward-filtering algorithm that operates on a virtually constructed discrete-time embedded Markov chain that mirrors the patient's continuous-time state trajectory. We demonstrate the prognostic utility of the HASMM in a critical care prognosis setting using a real-world dataset for patients admitted to the Ronald Reagan UCLA Medical Center. In particular, we show that using HASMMs, a patient's clinical deterioration can be predicted 8-9 hours prior to intensive care unit admission, with a 22% AUC gain compared to the Rothman index, which is the state-of-the-art critical care risk scoring technology.

We give a novel formal theoretical framework for unsupervised learning with two distinctive characteristics. First, it does not assume any generative model and based on a worst-case performance metric. Second, it is comparative, namely performance is measured with respect to a given hypothesis class. This allows to avoid known computational hardness results and improper algorithms based on convex relaxations. We show how several families of unsupervised learning models, which were previously only analyzed under probabilistic assumptions and are otherwise provably intractable, can be efficiently learned in our framework by convex optimization.

Pentesting tools like Metasploit, Burp, ExploitPack, BeEF, etc. are used by security practitioners to identify possible vulnerability points and to assess compliance with security policies. Pentesting tools come with a library of known exploits that have to be configured or customized for your particular environment. This configuration typically takes the form of a DSL or a set of fairly complex UIs to configure individual attacks. There are two major shortcomings with this approach (1) scanning doesn't yield perfect knowledge (2) scanning generates significant network traffic and can run for a very long time on a large network (Sarraute). It is perhaps due to these shortcomings (and maybe 0day exploits) that "most testing tools, provide no guarantee of soundness. Indeed, in the last few years, several reports have shown that state-of-the-art web application scanners fail to detect a significant number of vulnerabilities in test applications" (Doupé).

A lot of DJs and music producers are starting to wonder how these technologies could be implemented in their fields. In this article, DJTT's Steven Maude takes deep dive into current AI music projects, and how they could change the process of music creation in the very near future. From language translation, self-driving cars, to beating humans at traditional games or learning to play classic games from the modern era, artificial intelligence (AI) is a big deal in computer science right now. Thanks to the large data stores that, for better or worse, technology giants are collecting, and powerful graphics cards accelerating the math required, we're in a time of rapid progress in diverse fields. The natural question for DJs and producers: what are the possible implications for AI in music? But big technology names have looked at applying artificial intelligence techniques to music creation.

We introduce a novel multivariate random process producing Bernoulli outputs per dimension, that can possibly formalize binary interactions in various graphical structures and can be used to model opinion dynamics, epidemics, financial and biological time series data, etc. We call this a Bernoulli Autoregressive Process (BAR). A BAR process models a discrete-time vector random sequence of $p$ scalar Bernoulli processes with autoregressive dynamics and corresponds to a particular Markov Chain. The benefit from the autoregressive dynamics is the description of a $2^p\times 2^p$ transition matrix by at most $pd$ effective parameters for some $d\ll p$ or by two sparse matrices of dimensions $p\times p^2$ and $p\times p$, respectively, parameterizing the transitions. Additionally, we show that the BAR process mixes rapidly, by proving that the mixing time is $O(\log p)$. The hidden constant in the previous mixing time bound depends explicitly on the values of the chain parameters and implicitly on the maximum allowed in-degree of a node in the corresponding graph. For a network with $p$ nodes, where each node has in-degree at most $d$ and corresponds to a scalar Bernoulli process generated by a BAR, we provide a greedy algorithm that can efficiently learn the structure of the underlying directed graph with a sample complexity proportional to the mixing time of the BAR process. The sample complexity of the proposed algorithm is nearly order-optimal as it is only a $\log p$ factor away from an information-theoretic lower bound. We present simulation results illustrating the performance of our algorithm in various setups, including a model for a biological signaling network.

Pat Bagley is easily my favorite political cartoonist, period. For the politically aware in Utah, he is almost legendary, enjoying superstar status. I've been aware of him since I was a kid, and I always loved his cartoons. Not only does his artistic style appeal to me, he has a way of illustrating a situation in politics that explains it more clearly than a thousand words. His cartoons are humorous, though darkly so. And with every one, you can't help but feel he's had the last word.

So you report with reasonable accuracies what the sentiment about a particular brand or product is. After publishing this report, your client comes back to you and says "Hey this is good. Now can you tell me ways in which I can convert the negative sentiments into positive sentiments?" – Sentiment Analysis stops there and we enter the realms of Opinion Mining. Opinion Mining is about having a deeper understanding of the review that was written. Typically, a detailed review will not just have a sentiment attached to it. It will have information and valuable feedback that can literally help to build the next strategy.

This is the official code repository for Machine Learning with TensorFlow. Warning: The book will be released in a month or two, so this repo is a pre-release of the entire code. I will be heavily updating this repo in the coming weeks. Stay tuned, and follow along! Get started with machine learning using TensorFlow, Google's latest and greatest machine learning library.