Find out how AI, Machine Learning and Sentiment Analysis are being applied to Finance in a new conference organized by UNICOM Seminars Ltd in Hong Kong on 14-15 March 2017. Technology innovations meet greatest success in business when these are entirely'client focussed'. Developments in the retail sector, which is consumer-led, are addressing client demand for more personalised, faster and competitive services. Artificial Intelligence, Machine Learning and Sentiment Analysis are changing the way in which these services are offered. In particular, Financial Organisations are creating and leveraging such innovation in the domain of wealth management.

Sum-product networks have recently emerged as an attractive representation due to their dual view as a special type of deep neural network with clear semantics and a special type of probabilistic graphical model for which inference is always tractable. Those properties follow from some conditions (i.e., completeness and decomposability) that must be respected by the structure of the network. As a result, it is not easy to specify a valid sum-product network by hand and therefore structure learning techniques are typically used in practice. This paper describes the first online structure learning technique for continuous SPNs with Gaussian leaves. We also introduce an accompanying new parameter learning technique.

Artificial Neural Networks (ANNs) have received increasing attention in recent years with applications that span a wide range of disciplines including vital domains such as medicine, network security and autonomous transportation. However, neural network architectures are becoming increasingly complex and with an increasing need to obtain real-time results from such models, it has become pivotal to use parallelization as a mechanism for speeding up network training and deployment. In this work we propose an implementation of Network Parallel Training through Cannon's Algorithm for matrix multiplication. We show that increasing the number of processes speeds up training until the point where process communication costs become prohibitive; this point varies by network complexity. We also show through empirical efficiency calculations that the speedup obtained is superlinear.

Humans are not only adept in recognizing what class an input instance belongs to (i.e., classification task), but perhaps more remarkably, they can imagine (i.e., generate) plausible instances of a desired class with ease, when prompted. Inspired by this, we propose a framework which allows transforming Cascade-Correlation Neural Networks (CCNNs) into probabilistic generative models, thereby enabling CCNNs to generate samples from a category of interest. CCNNs are a well-known class of deterministic, discriminative NNs, which autonomously construct their topology, and have been successful in giving accounts for a variety of psychological phenomena. Our proposed framework is based on a Markov Chain Monte Carlo (MCMC) method, called the Metropolis-adjusted Langevin algorithm, which capitalizes on the gradient information of the target distribution to direct its explorations towards regions of high probability, thereby achieving good mixing properties. Through extensive simulations, we demonstrate the efficacy of our proposed framework.

Artificial Neural Networks(ANN) has been phenomenally successful on various pattern recognition tasks. However, the design of neural networks rely heavily on the experience and intuitions of individual developers. In this article, the author introduces a mathematical structure called MLP algebra on the set of all Multilayer Perceptron Neural Networks(MLP), which can serve as a guiding principle to build MLPs accommodating to the particular data sets, and to build complex MLPs from simpler ones.

Both generative adversarial networks (GAN) in unsupervised learning and actor-critic methods in reinforcement learning (RL) have gained a reputation for being difficult to optimize. Practitioners in both fields have amassed a large number of strategies to mitigate these instabilities and improve training. Here we show that GANs can be viewed as actor-critic methods in an environment where the actor cannot affect the reward. We review the strategies for stabilizing training for each class of models, both those that generalize between the two and those that are particular to that model. We also review a number of extensions to GANs and RL algorithms with even more complicated information flow. We hope that by highlighting this formal connection we will encourage both GAN and RL communities to develop general, scalable, and stable algorithms for multilevel optimization with deep networks, and to draw inspiration across communities.

Influence diagrams provide a compact graphical representation of decision problems. Several algorithms for the quick computation of their associated expected utilities are available in the literature. However, often they rely on a full quantification of both probabilistic uncertainties and utility values. For problems where all random variables and decision spaces are finite and discrete, here we develop a symbolic way to calculate the expected utilities of influence diagrams that does not require a full numerical representation. Within this approach expected utilities correspond to families of polynomials. After characterizing their polynomial structure, we develop an efficient symbolic algorithm for the propagation of expected utilities through the diagram and provide an implementation of this algorithm using a computer algebra system. We then characterize many of the standard manipulations of influence diagrams as transformations of polynomials. We also generalize the decision analytic framework of these diagrams by defining asymmetries as operations over the expected utility polynomials.

Appendix A. Relational MDs and the UCI Property Here, we formally extend the class of matching dependencies (MDs) introduced in Section 2.1, which we will call classical MDs, to the larger class of relational MDs. This extension is motivated by the application of MDs to blocking for entity resolution, but applications can be easily foreseen in other areas where declarative relational knowledge may be useful in combination with matching and merging. We also identify classes of relational MDs for which a single clean instance exists, no matter how the MDs are enforced, that can be computed through the chase procedure in polynomial time in the size of the database on which the MDs are enforced. We say that the MDs (in some cases in combination with an initial instance) have the unique clean instance property (UCI property). More details can be found in [11, 6, 7]. Definition 1. the form: Given a relational schema R, a relational MD is a formula of ϕ: t

From a practical point of view, computing implication bases of formal contexts is a challenging task. The reason for this is twofold: on the one hand, bases of formal contexts can be of exponential size [14] (see also an earlier work [12] for the same result presented in different terms), and thus just writing out the result can take a long time. On the other hand, even in cases where implication bases can be small, efficient methods to compute them are unknown in general, and running times may thus be much higher than necessary. This is particularly true for computing the canonical basis, where only very few algorithms [9, 15] are known, which all in addition to the canonical basis have to compute the complete concept lattice. The authors of this work are given in alphabetical order. No priority in authorship is implied. 2 Daniel Borchmann, Tom Hanika, and Sergei Obiedkov Approaches to tackle this problem are to parallelize existing algorithms [13], or restrict attention to implication bases that are more amenable to algorithmic treatment, such as proper premises [16] or D-bases [1].

January 17, 2017 --The dream of useful quantum computing may have just come one step closer. Australian researchers are combining two of the hottest topics in science: quantum computing and machine learning. Specifically, they've succeeded in training an algorithm to predict the evolving state of a simple quantum computer. Such an understanding allows real time stabilization of the system, much as tightrope walker uses a pole for balance, according to a paper published Monday in Nature Communications. That would be a big deal for everyone – from Silicon Valley to Washington, D.C.