Divide and Conquer (DC) is conceptually well suited to high-dimensional optimization by decomposing a problem into multiple small-scale sub-problems. However, appealing performance can be seldom observed when the sub-problems are interdependent. This paper suggests that the major difficulty of tackling interdependent sub-problems lies in the precise evaluation of a partial solution (to a sub-problem), which can be overwhelmingly costly and thus makes sub-problems non-trivial to conquer. Thus, we propose an approximation approach, named Divide and Approximate Conquer (DAC), which reduces the cost of partial solution evaluation from exponential time to polynomial time. Meanwhile, the convergence to the global optimum (of the original problem) is still guaranteed. The effectiveness of DAC is demonstrated empirically on two sets of non-separable high-dimensional problems.

Though with progress, model learning and performing posterior inference still remains a common challenge for using deep generative models, especially for handling discrete hidden variables. This paper is mainly concerned with algorithms for learning Helmholz machines, which is characterized by pairing the generative model with an auxiliary inference model. A common drawback of previous learning algorithms is that they indirectly optimize some bounds of the targeted marginal log-likelihood. In contrast, we successfully develop a new class of algorithms, based on stochastic approximation (SA) theory of the Robbins-Monro type, to directly optimize the marginal log-likelihood and simultaneously minimize the inclusive KL-divergence. The resulting learning algorithm is thus called joint SA (JSA). Moreover, we construct an effective MCMC operator for JSA. Our results on the MNIST datasets demonstrate that the JSA's performance is consistently superior to that of competing algorithms like RWS, for learning a range of difficult models.

Learning the "blocking" structure is a central challenge for high dimensional data (e.g., gene expression data). Recently, a sparse singular value decomposition (SVD) has been used as a biclustering tool to achieve this goal. However, this model ignores the structural information between variables (e.g., gene interaction graph). Although typical graph-regularized norm can incorporate such prior graph information to get accurate discovery and better interpretability, it fails to consider the opposite effect of variables with different signs. Motivated by the development of sparse coding and graph-regularized norm, we propose a novel sparse graph-regularized SVD as a powerful biclustering tool for analyzing high-dimensional data. The key of this method is to impose two penalties including a novel graph-regularized norm ($|\pmb{u}|\pmb{L}|\pmb{u}|$) and $L_0$-norm ($\|\pmb{u}\|_0$) on singular vectors to induce structural sparsity and enhance interpretability. We design an efficient Alternating Iterative Sparse Projection (AISP) algorithm to solve it. Finally, we apply our method and related ones to simulated and real data to show its efficiency in capturing natural blocking structures.

Traditional theories of social models conceptualize teams as distributed processors, disregarding the interdependence necessary to multi-task. Yet, interdependence characterizes social behavior. Instead, traditional theory favor cooperation, a state of least entropy production (LEP), without understanding the causes, limits or consequences of cooperation. As a simple example of interdependence, foraging prey overgraze forests free of predators. In our model, interdependence creates uncertainty, tradeoffs and signals (e.g., prices, coordination, innovation). Unlike individuals, the ability of teams to multitask reflects a quantum-like entanglement that represents maximum entropy production (MEP) when solving the problems signaled by society to improve its welfare. Our model supports findings that evolution in nature is driven by the MEP from making intelligent choices. Exploiting interdependence improves team intelligence, improves performance and reduces the risk of human error; forced cooperation disorganizes it by increasing the risk of error; e.g., if team cooperation improves teamwork, widespread forced cooperation in an autocracy or bureaucracy reduces social intelligence by adding unnecessary noise to signals. In our model, competition between teams self-organizes outsiders willing to sort through the noise for signals of the choices that improve social welfare (e.g., teams in courtrooms; science; entertainment; sports; businesses). Social systems organized around competition (e.g., stronger signals from robust checks and balances) better control a society by more correctly sizing teams to solve problems with fewer errors compared to autocracies or bureaucracies. Overall, we predict, the density of MEP directed at solving problems in a society with the constraints imposed from strong checks and balances, yet able to freely self-organize its labor and capital within those constraints, is denser.

As autonomous systems are becoming more and more pervasive, they often have to make decisions concerning moral and ethical values. There are many approaches to incorporating moral values in autonomous decision-making that are based on some sort of logical deduction. However, we argue here, in order for decision-making to seem persuasive to humans, it needs to reflect human values and judgments. Employing some insights from our ongoing researchusing features of the blackboard architecture for a context-aware recommender system, and a legal decision-making system that incorporates supra-legal aspects, we aim to explore if this architecture can also be adapted to implement a moral decision-making system that generates rationales that are persuasive to humans. Our vision is that such a system can be used as an advisory system to consider a situation from different moral perspectives, and generate ethical pros and cons of taking a particular course of action in a given context.

This paper describes one of the future images of the sleep monitoring system. The new technology should satisfy the following requirements: (1) noninvasive, (2) low cost and (3) long-term monitoring. What we propose here is the sleep monitoring system based on the human body vibrations sensed by the mattress type pressure sensors that gradually improves its estimation performance to the particular user by learning collected data and reconstructing its classifier.%In order to learn the data, however, the system needs the vibration data mapped to the appropriate sleep stages. As the solution to the problem, we use the existing approximate sleep stage estimation method. The experimental results reveal that (1)there is only a slightly difference between the accuracies of the two classifiers; the one trained the original dataset plus PSG based sleep stage labeled data; the other one trained the original dataset plus approximate sleep stage labeled data; (2 )Adding a particular user's several days data to the training data improves the accuracy of the original classifiers. The REM estimation accuracy is 87% in maximum. From those results, the contribution of this research is suggesting the way to personalize sleep estimation, and proving the effectiveness.

Two big recent revolutions: machine learning technologies; such as “deep learning” in Artificial Intelligence (AI), and personal genome informatics in biomedical science, provide us with new opportunities for understanding human happiness. Our ongoing important challenges are to discover our own truly meaningful personal happiness with the aid of AI and personal genome technologies. We have been developing a personal genome information agent entitled MyFinder, which supports searching for our inherited talents and maximizes our potential for a meaningful life. In the MyFinder project, we have provided a crowd-sourced DIY (Do it yourself) genomics research platform and conducted various “citizen science” projects in health and wellness. In this paper, we discuss how machine learning technologies and personal genome informat-ics might contribute to happiness sciences. We introduce the “Social Intelligence Genomics and Empathy-Building Study” and report the preliminary results of applying deep learning and six other machine learning algorithms for predicting social intelligence levels from nine SNPs genetic profiles. We dis-cuss the possibilities and limitations of applying machine learning technologies for personal happiness trait prediction. We also discuss future AI challenges in the context of wellbeing computing.

We have developed a visualization system of dementia care skills based on multimodal communication features. The purpose of our system is to provide effective learning of dementia care to trainees. As dementia care skills are difficult to visualize and describe, they are hard to acquire for trainees. We focus on HumanitudeR; a non-pharmacological comprehensive intervention with verbal and non-verbal communication, which is a care methodology of French-origin for the vulnerable elderlies. The multimodal methodology utilizes four techniques to relate to elderly with dementia (i.e., gaze, speak, touch, opportunities to stand on their feet). We analyzed the care videos of Humanitude instructors to extract multimodal communication features. We designed and filmed video contents demonstrating the extracted features. These have shown to be effective, in combination with practice and reflection, to acquire dementia care skills. The trainees could use the system for self-reflection and teaching.

We revisit a series of studies on the work of multidisciplinary medical teams with a view to identifying opportunities for the use of intelligent systems to support their complex cooperative work, and the challenges that might arise in developing such systems. We focus specially on the activities performed during the multidisciplinary medical team meeting (MDTM) and review the literature on MDTMs, as well as our own longitudinal analysis of several MDTs in a large teaching hospital over a period of ten years.

This paper and use of autonomous weapons systems has been will discuss the moral and ethical questions that arise in the one of the outcomes of the counterterrorism and counterinsurgency use of lethally autonomous technology for military purposes operations in Iraq and Afghanistan. The asymmetrical and how the forms of subjectivity and moral agency that battlefields of these theaters, where no frontline it creates could be highly counterproductive to mission provides a buffer between combatants and civilians and effectiveness, diplomacy and conflict resolution and prevention.