Abstract — The paper proposes a hypernetwork-based method for stock market prediction through a binary time series problem. Hypernetworks are a random hypergraph structure of higher-order probabilistic relations of data. The problem we tackle concerns the prediction of price movements (up/down) on stock markets. Compared to previous approaches, the proposed method discovers a large population of variable subpatterns, i.e. local and global patterns, using a novel evolutionary hypernetwork. An output is obtained from combining these patterns. In the paper, we describe two methods for assessing the prediction quality of the hypernetwork approach. Applied to the Dow Jones Industrial Average Index and the Korea Composite Stock Price Index data, the experimental results show that the proposed method effectively learns and predicts the time series information. In particular, the hypernetwork approach outperforms other machine learning methods such as support vector machines, naive Bayes, multilayer perceptrons, and k-nearest neighbors. I.

Abstract—As the amount of multimedia data grows larger and multi-modal information is widespread, requirements for methods are increasing which can be used to analyze composite information and retrieve related items of one modality based on another modality. For contents-based retrieval, models that incorporate multiple modalities concurrently are recognized as a mandatory approach. In this study, we propose a method to reconstruct and retrieve images based on text-to-image cross-modal recall by hypernetworks. In our method, a probabilistic graphical model called hypernetwork learns the

Abstract. Conventional methods for multimodal data retrieval use text-tag based or cross-modal approaches such as tag-image co-occurrence and canonical correlation analysis. Since there are differences of granularity in text and image features, however, approaches based on lower-order relationship between modalities may have limitations. Here, we propose a novel text and image keyword generation method by cross-modal associative learning and inference with multimodal queries. We use a modified hypernetwork model, i.e. layered hypernetworks (LHNs) which consists of the first (lower) layer and the second (upper) layer which has more than two modality-dependent hypernetworks and one modality-integrating hypernetwork, respectively. LHNs learn higher-order associative relationships between text and image modalities by training on an example set. After training, LHNs are used to extend multimodal queries by generating text and image keywords via cross-modal inference, i.e. text-toimage and image-to-text. The LHNs are evaluated on Korean magazine articles with images on women fashions and life-style. Experimental results show that the proposed method generates vision-language cross-modal keywords with high accuracy. The results also show that multimodal queries improve the accuracy

As agents become ubiquitous in virtual as well as physical worlds, the importance of learning from real-life human interaction is increasing. Here we explore new learning and teaching strategies for an agent situated in a digital cinema environment to solve a language-vision translation problem by playing a multimodal memory game with humans. We discuss the challenges for machine learners, i.e. learning architectures and algorithms, required to deal with this kind of long-lasting, dynamic scenario. We also discuss the challenges for human teachers to address the new machine learning issues. Based on our preliminary experimental results using the hypernetwork learning architecture we argue for self-teaching cognitive agents that actively interact with humans to generate queries and examples to evaluate and teach themselves.

Abstract — Evolutionary hypernetworks (EHNs) are recently introduced models for learning higher-order probabilistic relations of data by an evolutionary self-organizing process. We present a method that enables EHNs to learn and generate music from examples. Short-term and long-term sequential patterns can be extracted and combined to generate music with various styles by our method. Based on a music corpus consisting of several genres and artists, an EHN generates genre-specific or artist-dependent music fragments when a fraction of score is given as a cue. Our method shows about 88% of success rate in partial music completion task. By inspecting hyperedges in the trained hypernetworks, we can extract a set of arguments that constitutes melodic structures in music. I.

Abstract. We proposed a molecular evolutionary learning model (DNA hypernetworks) to solve digit pattern recognition problems and executed in vitro experiments. By applying data mining technique for large scale digit data, we obtained 25 feature pixels from 16 by 16 pixels. From the DNA hypernetwork structure perspective, the selected pixels as the network nodes are encoded to DNA sequences, and order-3 hyperedge DNA strands were generated by their random combination. The classifiers for digit recognition are directly evolved from the first hyperedge DNA pool called initial library with a set of training data set by DNA computing operation such as hybridization, size fraction, splitting and amplification. A set of test examples is evaluated; the classification performance is improved by repeatedly updating full matched classifiers. This study shows that pattern classifiers can be learned with DNA chemistry in vitro and suggests application of DNA computing in other pattern recognition such as direct gene expression pattern or image pattern analyses with DNA computer. References

journal homepage: www.elsevier.com/locate/biosystems

Abstract. Humans can associate vision and language modalities and thus generate mental imagery, i.e. visual images, from linguistic input in an environment of unlimited inflowing information. Inspired by human memory, we separate a text-to-image retrieval task into two steps: 1) text-to-image conversion (generating visual queries for the 2 step) and 2) image-to-image retrieval task. This separation is advantageous for inner representation visualization, learning incremental dataset, using the results of content-based image retrieval. Here, we propose a visual query expansion method that simulates the capability of human associative memory. We use a hyperenetwork model (HN) that combines visual words and linguistic words. HNs learn the higher-order cross-modal associative relationships incrementally on a set of image-text pairs in sequence. An incremental HN generates images by assembling visual words based on linguistic cues. And we retrieve similar images with the generated visual query. The method is evaluated on 26 video clips of ‘Thomas and Friends’. Experiments show the performance of successive image retrieval rate up to 98.1 % with a single text cue. It shows the additional potential to generate the visual query with several text cues simultaneously.

Abstract. How humans infer probable information from the limited observed data? How they are able to build on little knowledge about the context in hand? Is the human memory repeatedly constructing and reconstructing the events that are being recalled? These are a few questions that we are interested in answering with our multimodal memory game (MMG) platform that studies human memory and their behaviors while watching and remembering TV dramas for a better recall. Based on the preliminary results of human learning obtained from the MMG games, we attempt to show that the human memory recall improves steadily with the number of game sessions. As an example case, we provide a comparison for the text-to-text and text-image-to-text learning and demonstrate that the addition of image context is useful in improving the learning.

Abstract — Exploring microRNA (miRNA) and mRNA regulatory interactions may give new insights into diverse biological phenomena. While elucidating complex miRNA-mRNA interactions has been studied with experimental and computational approaches, it is still difficult to infer miRNA-mRNA regulatory modules. Here we present a novel method for identifying functional miRNA-mRNA modules from heterogeneous expression data. The proposed approach is layered hypernetworks consisting of two layers which are the layer of modality-dependent hypernetworks and of an integrating hypernetwork. The layered hypernetwork model is suitable for detecting relationships between heterogeneous modalities. Applied to the analysis of miRNA and mRNA expression profiles on multiple human cancers, the proposed model identifies oncogenic miRNA-mRNA regulatory modules. The experimental results show that our method provides a competitive performance to support vector machines, and outperforms other standard machine learning algorithms. The biological significance of the discovered miR-NA-mRNA modules were validated by literature reviews. R I.