Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with a prohibitive computational cost. In this paper we develop a new theoretical framework casting dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes. A direct result of this theory gives us tools to model uncertainty with dropout NNs -- extracting information from existing models that has been thrown away so far. This mitigates the problem of representing uncertainty in deep learning without sacrificing either computational complexity or test accuracy. We perform an extensive study of the properties of dropout's uncertainty. Various network architectures and non-linearities are assessed on tasks of regression and classification, using MNIST as an example. We show a considerable improvement in predictive log-likelihood and RMSE compared to existing state-of-the-art methods, and finish by using dropout's uncertainty in deep reinforcement learning.

In the previous article in the series Hidden Markov Models were introduced. They were discussed in the context of the broader class of Markov Models. They were motivated by the need for quantitative traders to have the ability to detect market regimes in order to adjust how their quant strategies are managed. In particular it was mentioned that "various regimes lead to adjustments of asset returns via shifts in their means, variances/volatilities, serial correlation and covariances, which impact the effectiveness of time series methods that rely on stationarity". This has a significant bearing on how trading strategies are modified throughout the strategy lifecycle.

We consider a problem of data integration. Consider determining which genes affect a disease. The genes, which we call predictor objects, can be measured in different experiments on the same individual. We address the question of finding which genes are predictors of disease by any of the experiments. Our formulation is more general. In a given data set, there are a fixed number of responses for each individual, which may include a mix of discrete, binary and continuous variables. There is also a class of predictor objects, which may differ within a subject depending on how the predictor object is measured, i.e., depend on the experiment. The goal is to select which predictor objects affect any of the responses, where the number of such informative predictor objects or features tends to infinity as sample size increases. There are marginal likelihoods for each way the predictor object is measured, i.e., for each experiment. We specify a pseudolikelihood combining the marginal likelihoods, and propose a pseudolikelihood information criterion. Under regularity conditions, we establish selection consistency for the pseudolikelihood information criterion with unbounded true model size, which includes a Bayesian information criterion with appropriate penalty term as a special case. Simulations indicate that data integration improves upon, sometimes dramatically, using only one of the data sources.

Bayesian optimization has become a fundamental global optimization algorithm in many problems where sample efficiency is of paramount importance. Recently, there has been proposed a large number of new applications in fields such as robotics, machine learning, experimental design, simulation, etc. In this paper, we focus on several problems that appear in robotics and autonomous systems: algorithm tuning, automatic control and intelligent design. All those problems can be mapped to global optimization problems. However, they become hard optimization problems. Bayesian optimization internally uses a probabilistic surrogate model (e.g.: Gaussian process) to learn from the process and reduce the number of samples required. In order to generalize to unknown functions in a black-box fashion, the common assumption is that the underlying function can be modeled with a stationary process. Nonstationary Gaussian process regression cannot generalize easily and it typically requires prior knowledge of the function. Some works have designed techniques to generalize Bayesian optimization to nonstationary functions in an indirect way, but using techniques originally designed for regression, where the objective is to improve the quality of the surrogate model everywhere. Instead optimization should focus on improving the surrogate model near the optimum. In this paper, we present a novel kernel function specially designed for Bayesian optimization, that allows nonstationary behavior of the surrogate model in an adaptive local region. In our experiments, we found that this new kernel results in an improved local search (exploitation), without penalizing the global search (exploration). We provide results in well-known benchmarks and real applications. The new method outperforms the state of the art in Bayesian optimization both in stationary and nonstationary problems.

In recent years, we've seen a resurgence in AI, or artificial intelligence, and machine learning. Machine learning has led to some amazing results, like being able to analyze medical images and predict diseases on-par with human experts. Google's AlphaGo program was able to beat a world champion in the strategy game go using deep reinforcement learning. Machine learning is even being used to program self driving cars, which is going to change the automotive industry forever. Imagine a world with drastically reduced car accidents, simply by removing the element of human error.

The present invention relates generally to data mining and more specifically to a classifier and inducer used for data mining. Many data mining tasks require classification of data into classes. Typically, a classifier classifies the data into the classes. For example, loan applications can be classified into either "approve" or "disapprove" classes. The classifier provides a function that maps (classifies) a data item (instance or record; records and instances are used interchangeably hereinafter) into one of several predefined classes. More specifically, the classifier predicts one attribute of a set of data given one or more attributes. For example, in a database of iris flowers, a classifier can be built to predict the type of iris (iris-setosa, iris-versicolor or iris-virginica) given the petal length, sepal length and sepal width. The attribute being predicted (in this case, the type of iris) is called the label, and the attributes used for prediction are called the descriptive attributes. A classifier is generally constructed by an inducer.

The current situation with malware naming conventions is in disarray. Different antivirus vendors use different naming conventions and sometimes they don't follow their own standards. Let's look at a few results for a random virus. These are the results from VirusTotal, a meta-antivirus scanning service. We can see that it is a Trojan malware with some vendors (Dr.Web and TrendMicro) setting the family as StartPage, some saying it's in the Agent family, some saying it is in the FakeAV family and some saying it is Generic "KR" malware.

Bayesian networks (BNs) are graphical models that are useful for representing high-dimensional probability distributions. There has been a great deal of interest in recent years in the NP-hard problem of learning the structure of a BN from observed data. Typically, one assigns a score to various structures and the search becomes an optimization problem that can be approached with either deterministic or stochastic methods. In this paper, we walk through the space of graphs by modeling the appearance and disappearance of edges as a birth and death process and compare our novel approach to the popular Metropolis-Hastings search strategy. We give empirical evidence that the birth and death process has superior mixing properties.

Introduction In the previous article, we described combat performance in the Artificial Intelligence PK Gold Medal Stenography Competition and told the story behind the annual Alibaba Cloud meeting's Man VS Machine competition. Are there any curious technology geeks out there? What was the on-site real-time transcription system? What on earth is the core of a speech recognition system? How come the Alibaba Cloud iDST speech recognition system is so accurate?

This paper begins with considering the identification of sparse linear time-invariant networks described by multivariable ARX models. Such models possess relatively simple structure thus used as a benchmark to promote further research. With identifiability of the network guaranteed, this paper presents an identification method that infers both the Boolean structure of the network and the internal dynamics between nodes. Identification is performed directly from data without any prior knowledge of the system, including its order. The proposed method solves the identification problem using Maximum a posteriori estimation (MAP) but with inseparable penalties for complexity, both in terms of element (order of nonzero connections) and group sparsity (network topology). Such an approach is widely applied in Compressive Sensing (CS) and known as Sparse Bayesian Learning (SBL). We then propose a novel scheme that combines sparse Bayesian and group sparse Bayesian to efficiently solve the problem. The resulted algorithm has a similar form of the standard Sparse Group Lasso (SGL) while with known noise variance, it simplifies to exact re-weighted SGL. The method and the developed toolbox can be applied to infer networks from a wide range of fields, including systems biology applications such as signaling and genetic regulatory networks.