Representation (systemics)

About: Representation (systemics) is a research topic. Over the lifetime, 33821 publications have been published within this topic receiving 475461 citations.

Multi-View 3D Object Retrieval With Deep Embedding Network

Abstract: In multi-view 3D object retrieval, each object is characterized by a group of 2D images captured from different views. Rather than using hand-crafted features, in this paper, we take advantage of the strong discriminative power of convolutional neural network to learn an effective 3D object representation tailored for this retrieval task. Specifically, we propose a deep embedding network jointly supervised by classification loss and triplet loss to map the high-dimensional image space into a low-dimensional feature space, where the Euclidean distance of features directly corresponds to the semantic similarity of images. By effectively reducing the intra-class variations while increasing the inter-class ones of the input images, the network guarantees that similar images are closer than dissimilar ones in the learned feature space. Besides, we investigate the effectiveness of deep features extracted from different layers of the embedding network extensively and find that an efficient 3D object representation should be a tradeoff between global semantic information and discriminative local characteristics. Then, with the set of deep features extracted from different views, we can generate a comprehensive description for each 3D object and formulate the multi-view 3D object retrieval as a set-to-set matching problem. Extensive experiments on SHREC’15 data set demonstrate the superiority of our proposed method over the previous state-of-the-art approaches with over 12% performance improvement.

From simple features to sophisticated evaluation functions

Abstract: This paper discusses a practical framework for the semiautomatic construction of evaluation-functions for games. Based on a structured evaluation function representation, a procedure for exploring the feature space is presented that is able to discover new features in a computationally feasible way. Besides the theoretical aspects, related practical issues such as the generation of training positions, feature selection, and weight fitting in large linear systems are discussed. Finally, we present experimental results for Othello, which demonstrate the potential of the described approach.

Explicit representation of terms defined by counter examples

Abstract: Anti-unification guarantees the existence of a term which is an explicit representation of the most specific generalization of a collection of terms. This provides a formal basis for learning from examples. Here we address the dual problem of computing a generalization given a set of counter examples. Unlike learning from examples an explicit, finite representation for the generalization does not always exist. We show that the problem is decidable by providing an algorithm which, given an implicit representation will return a finite explicit representation or report that none exists. Applications of this result to the problem of negation as failure and to the representation of solutions to systems of equations and inequations are also mentioned.

Temporal uncertainties in interactions among real-time objects

Abstract: A model of a distributed real-time system which supports reasoning about the consistency and accuracy of real-time data and about the performance of real-time communication protocols is presented. The conventional object model is extended into a model of a real-time (RT-) object which incorporates a real-time clock as a mechanism for initiating an object action as a function of real time. The notion of accuracy as referring to the time gap between a state variable in the external world and its representation in a real-time computer system is adopted. The effects of the temporal uncertainties of different classes of communication protocols on the consistency and the accuracy of RT-objects are analyzed. Finally, an approach to structuring fault-tolerant RT-objects in the form of active object replicas is discussed, and the effects of a failure of a task in a replica on the responsiveness of remote objects are analyzed. >