We introduce CIM, a Commonsense Inference Memory system utilizing both Extended Semantic Networks and Bayesian Networks that builds upon the commonsense knowledgebase ConceptNet. CIM introduces a new technique for self-assembling Bayesian Networks that allows only relevant parts of the commonsense database to affect the inference. The Bayesian Network include the activity in the input sentences and the related activities appearing in the commonsense database. They are used to interpret and infer the meaning of the set of sentences input. Without self-assembled networks, only relevant inference is performed, speeding up performance of reasoning with commonsense knowledge. We demonstrate that our system can disambiguate the needs of the user even if they do not state them directly, and do not use keywords. This ability would not be possible without either the use of commonsense or significant training. Eventually this approach may be applied to increase the effectiveness of other natural language understanding techniques as well.

We present a framework to represent and reason about narratives that combines logical and probabilistic representations of commonsense knowledge. Unlike most natural language understanding systems, which merely extract facts or semantic roles, our system builds probabilistic representations of the temporal sequence of world states and actions implied by a narrative. We use probabilistic actions to represent ambiguities and uncertainties in the narrative. We present algorithms that take a representation of a narrative, derive all possible interpretations of the narrative, and answer probabilistic queries by marginalizing over all the interpretations. With a focus on spatial contexts, we demonstrate our framework on an example narrative. To this end, we apply natural language pro- cessing (NLP) tools together with statistical approaches over common sense knowledge bases.

Sustainability requires emphasizing the importance of environmental causes and effects among design knowledge from heterogeneous stakeholders to make a sustainable decision. Recently, such causes and effects have been well developed in ontological representation, which has been challenged to generate and integrate multiple domain knowledge due to its domain specific characteristics. Moreover, it is too challengeable to represent heterogeneous, domain-specific design knowledge in a standardized way. Causal knowledge can meet the necessity of knowledge integration in domains. Therefore, this paper aims to develop a causal knowledge integration system with the authors’ previous mathematical causal knowledge representation.

The research project here described aims to contribute to the issue of sustainability of buildings by improving the architectural design process with the development of a decision support tool for the architect. In particular, the research adopts the improvement of existing designs, namely encouraging energy-efficient redesigns while improving indoor environmental quality as its strategy to promote sustainability. Redesign strategy is considered not only to extend the life cycle of a building but also to contribute to the realization of the overall transition towards an efficient and clean climate. The starting point for this research is the question of how to develop an integral framework which enables the modelling of design knowledge through more energy-efficient dwellings with acceptable indoor comfort in the sustainability context so that it would be possible to deal with qualitative, quantitative, complex and contradictory information at the same time and integrate these into design decision-making processes. This modelling approach is considered to provide a link to developing a tool or a link to be embedded in an existing tool. In the development of such an approach, how Artificial Intelligence (AI) can facilitate an integral understanding of the aspects is raised as a methodological question in terms of information processing and knowledge integration in the form of a design decision support tool. By this way it will be possible to assess the performance of the end result with respect to design choices, beforehand.

We apply artificial intelligence techniques to perform data analysis and activity recognition in smart homes. Sensors embedded in smart home provide primary data for reasoning about observations. The final goal is to provide appropriate assistance for residents to complete their Daily living Activities. Here, we introduce a qualitative approach that considers spatiotemporal specifications of activities in the Activity Recognition Agent to do knowledge representation and reasoning about the observations. We consider different existing uncertainties within sensors observations and Observed Agent’s activities. In the introduced approach, the more details about environment context would cause the less activity recognition process complexity and more precise functionality. To represent the knowledge, we apply the fuzzy logic to represent the world state by the fuzzified received values from sensors. The knowledge would be represented in the fuzzy context frame. To reduce the amount of collected data, meaningful changes in sensors generated values are considered to do Activity Recognition. Applying possibility distributions for event occurrence orders and sequences within different scenarios of activities realization, we are able to generate hypotheses about future possible occur-able events. The possible occur-able events and fuzzy digit parameters of their possible happening moments are represented in matrix format. The hypotheses about possible future observable contexts are generated considering spatial, temporal and other environmental parameters and then they would be ranked. Our final goal is to better explain the observations. If no possible explanation about observation be found, it would be recognized as abnormal behavior. In the case that no expected event be observed, we can reason that maybe event has occurred but not triggered and so next available events in previously learned scenarios would be expected. The system patience for number of possible missed events depends to trade-off between the degrees of resident's forgetfulness and probability of events trigger by applied sensors.

The estimation of asset return distributions is crucial for determining optimal trading strategies. One convenient estimation approach selects a distribution model and estimates its parameters. The advantage of this approach is the ease with which probability distributions can be calibrated and applied in post-processing. The disadvantage of assuming a particular parametric distribution is that inferences and decisions depend critically on the choice of distribution. For example, asset returns frequently feature large "outlying" values, making distributions with light tails inapplicable. Semi-parametric methods attempt to capture the advantages but not the disadvantages of a parametric specification of a returns distribution by using a more flexible functional form. Most prominent among the semi-parametric distributions are mixtures of distributions. They provide a flexible specification and, under certain conditions, can approximate distributions of any form.

In Artificial Intelligence with Coalition Structure Generation (CSG) one refers to those cooperative complex problems that require to find an optimal partition, maximising a social welfare, of a set of entities involved in a system into exhaustive and disjoint coalitions. The solution of the CSG problem finds applications in many fields such as Machine Learning (covering machines, clustering), Data Mining (decision tree, discretization), Graph Theory, Natural Language Processing (aggregation), Semantic Web (service composition), and Bioinformatics. The problem of finding the optimal coalition structure is NP-complete. In this paper we present a greedy adaptive search procedure (GRASP) with path-relinking to efficiently search the space of coalition structures. Experiments and comparisons to other algorithms prove the validity of the proposed method in solving this hard combinatorial problem.

In this paper a novel neuro-fuzzy system is proposed where its learning is based on the creation of fuzzy relations by using new implication method without utilizing any exact mathematical techniques. Then, a simple memristor crossbar-based analog circuit is designed to implement this neuro-fuzzy system which offers very interesting properties. In addition to high connectivity between neurons and being fault-tolerant, all synaptic weights in our proposed method are always non-negative and there is no need to precisely adjust them. Finally, this structure is hierarchically expandable and can compute operations in real time since it is implemented through analog circuits. Simulation results show the efficiency and applicability of our neuro-fuzzy computing system. They also indicate that this system can be a good candidate to be used for creating artificial brain.

Multiple kernel learning (MKL), structured sparsity, and multi-task learning have recently received considerable attention. In this paper, we show how different MKL algorithms can be understood as applications of either regularization on the kernel weights or block-norm-based regularization, which is more common in structured sparsity and multi-task learning. We show that these two regularization strategies can be systematically mapped to each other through a concave conjugate operation. When the kernel-weight-based regularizer is separable into components, we can naturally consider a generative probabilistic model behind MKL. Based on this model, we propose learning algorithms for the kernel weights through the maximization of marginal likelihood. We show through numerical experiments that $\ell_2$-norm MKL and Elastic-net MKL achieve comparable accuracy to uniform kernel combination. Although uniform kernel combination might be preferable from its simplicity, $\ell_2$-norm MKL and Elastic-net MKL can learn the usefulness of the information sources represented as kernels. In particular, Elastic-net MKL achieves sparsity in the kernel weights.

Modern statistical applications involving large data sets have focused attention on statistical methodologies which are both efficient computationally and able to deal with the screening of large numbers of different candidate models. Here we consider computationally efficient variational Bayes approaches to inference in high-dimensional heteroscedastic linear regression, where both the mean and variance are described in terms of linear functions of the predictors and where the number of predictors can be larger than the sample size. We derive a closed form variational lower bound on the log marginal likelihood useful for model selection, and propose a novel fast greedy search algorithm on the model space which makes use of one step optimization updates to the variational lower bound in the current model for screening large numbers of candidate predictor variables for inclusion/exclusion in a computationally thrifty way. We show that the model search strategy we suggest is related to widely used orthogonal matching pursuit algorithms for model search but yields a framework for potentially extending these algorithms to more complex models. The methodology is applied in simulations and in two real examples involving prediction for food constituents using NIR technology and prediction of disease progression in diabetes.