Results 1 - 10 of 221

Loopy belief propagation for approximate inference: An empirical study. In:

by Kevin P Murphy , Yair Weiss , Michael I Jordan - Proceedings of Uncertainty in AI, , 1999
"... Abstract Recently, researchers have demonstrated that "loopy belief propagation" -the use of Pearl's polytree algorithm in a Bayesian network with loops -can perform well in the context of error-correcting codes. The most dramatic instance of this is the near Shannon-limit performanc ..."
Abstract - Cited by 676 (15 self) - Add to MetaCart
to the correct marginals. However, on the QMR network, the loopy be liefs oscillated and had no obvious relation ship to the correct posteriors. We present some initial investigations into the cause of these oscillations, and show that some sim ple methods of preventing them lead to the wrong results

Deep convolutional network cascade for facial point detection

by Yi Sun, Xiaogang Wang, Xiaoou Tang - In CVPR , 2013
"... We propose a new approach for estimation of the posi-tions of facial keypoints with three-level carefully designed convolutional networks. At each level, the outputs of multi-ple networks are fused for robust and accurate estimation. Thanks to the deep structures of convolutional networks, global hi ..."
Abstract - Cited by 45 (6 self) - Add to MetaCart
We propose a new approach for estimation of the posi-tions of facial keypoints with three-level carefully designed convolutional networks. At each level, the outputs of multi-ple networks are fused for robust and accurate estimation. Thanks to the deep structures of convolutional networks, global

M.: Linking social networks on the web with foaf: A semantic web case study

by Jennifer Golbeck, Matthew Rothstein , 2008
"... One of the core goals of the Semantic Web is to store data in distributed locations, and use ontologies and reasoning to aggregate it. Social networking is a large movement on the web, and social networking data using the Friend of a Friend (FOAF) vocabulary makes up a significant portion of all dat ..."
Abstract - Cited by 26 (1 self) - Add to MetaCart
networks. Using the semantics of the FOAF ontology and ap-plying Semantic Web reasoning techniques, we show that a significant percentage of profiles can be merged from multi-ple networks. We present results on how this affects network structure and what it says about the success of the Semantic Web.

Distributed Coevolutionary Genetic Algorithm for Optimal Design of Ad Hoc Injection Networks

by Pascal Bouvry, Enrique Alba
"... Abstract—Multi-hop ad-hoc networks allow establish-ing local groups of communicating devices in a self-organizing way. However, in a global setting such net-works fail to work properly due to network partitioning. This means that users locally interacting could eventu-ally spread and move away from ..."
Abstract - Add to MetaCart
each other and conse-quently loose their connections. Considering that de-vices are capable of communicating both locally (e.g. using Wi-Fi or Bluetooth) and additionally with remote devices (e.g. using GSM/UMTS links) the objective of our work is to optimize the way of inter-linking multi-ple network

SafetyNet: improving the availability of shared memory multiprocessors with global checkpoint/recovery

by Daniel J. Sorin, Milo M. K. Martin, Mark D. Hill, David A. Wood - In Proceedings of the 29th Annual International Symposium on Computer Architecture , 2002
"... We develop an availability solution, called SafetyNet, that uses a unified, lightweight checkpoint~recovery mechanism to support multiple long-latency fault detection schemes. At an abstract level, SafetyNet logically maintains multi-ple, globally consistent checkpoints of the state of a shared memo ..."
Abstract - Cited by 137 (10 self) - Add to MetaCart
We develop an availability solution, called SafetyNet, that uses a unified, lightweight checkpoint~recovery mechanism to support multiple long-latency fault detection schemes. At an abstract level, SafetyNet logically maintains multi-ple, globally consistent checkpoints of the state of a shared

Large-scale Video Classification with Convolutional Neural Networks

by Andrej Karpathy, George Toderici Sanketh Shetty, Thomas Leung, Rahul Sukthankar, Li Fei-fei
"... Convolutional Neural Networks (CNNs) have been es-tablished as a powerful class of models for image recog-nition problems. Encouraged by these results, we pro-vide an extensive empirical evaluation of CNNs on large-scale video classification using a new dataset of 1 million YouTube videos belonging ..."
Abstract - Cited by 68 (5 self) - Add to MetaCart
to 487 classes. We study multi-ple approaches for extending the connectivity of the a CNN in time domain to take advantage of local spatio-temporal information and suggest a multiresolution, foveated archi-tecture as a promising way of speeding up the training. Our best spatio-temporal networks display

Design and management of 3D chip multiprocessors using network-in-memory

by Feihui Li, Chrysostomos Nicopoulos, Thomas Richardson, Yuan Xie, Vijaykrishnan Narayanan, Mahmut K - in Proc. Int. Symp. Comput , 2006
"... Long interconnects are becoming an increasingly important problem from both power and performance perspectives. This mo-tivates designers to adopt on-chip network-based communication infrastructures and three-dimensional (3D) designs where multi-ple device layers are stacked together. Considering th ..."
Abstract - Cited by 72 (4 self) - Add to MetaCart
Long interconnects are becoming an increasingly important problem from both power and performance perspectives. This mo-tivates designers to adopt on-chip network-based communication infrastructures and three-dimensional (3D) designs where multi-ple device layers are stacked together. Considering

Convolutional Neural Networks for Sentence Classification

by Yoon Kim
"... We report on a series of experiments with convolutional neural networks (CNN) trained on top of pre-trained word vec-tors for sentence-level classification tasks. We show that a simple CNN with lit-tle hyperparameter tuning and static vec-tors achieves excellent results on multi-ple benchmarks. Lear ..."
Abstract - Cited by 21 (0 self) - Add to MetaCart
We report on a series of experiments with convolutional neural networks (CNN) trained on top of pre-trained word vec-tors for sentence-level classification tasks. We show that a simple CNN with lit-tle hyperparameter tuning and static vec-tors achieves excellent results on multi-ple benchmarks

on Neural Network

by M. R. Dileep, Ajit Danti
"... Objective: Gender Classification is one of the most important applications in Artificial Intelligent Systems. The objective of this research work is to classify the human gender based on multiple level decisions. Since many years, a great deal of effort has been made to gender recognition from face ..."
Abstract - Add to MetaCart
images. It is not straightforward to achieve the same accuracy level in real-world environment. The proposed approach can give solution to these problems. Methods: In this paper, multi-ple levels hierarchical techniques based on 3 Sigma control limits on Neural Network is applied for gender recognition

Developing active sensor networks with micro mobile robots

by Weihua Sheng, Girma Tewolde - in: Proceedings, International Conference on Electro/Information Technology , 2006
"... A new sensor network architecture called active sensor net-work (ASN) is proposed in this paper. By integrating multi-ple small, sensor network-friendly mobile robots into a tradi-tional sensor network, a closed-loop, dynamic, adaptive sen-sor network is formed. Such sensor networks have the fol-low ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
A new sensor network architecture called active sensor net-work (ASN) is proposed in this paper. By integrating multi-ple small, sensor network-friendly mobile robots into a tradi-tional sensor network, a closed-loop, dynamic, adaptive sen-sor network is formed. Such sensor networks have the fol
Results 1 - 10 of 221