Results 1  10
of
1,035
TreeStructure Architecture and VLSI Implementation
"... this paper. The proposed foldedtree architecture is designed by 0.8/m CMOS VLSI technology. The die size is 4.65x5.21 mm 2 and estimated clock rate is about 34MHz, which satisfies most realtime applications. Since it is basically a mean squared error computation circuit, various kinds of VQ algori ..."
Abstract
 Add to MetaCart
this paper. The proposed foldedtree architecture is designed by 0.8/m CMOS VLSI technology. The die size is 4.65x5.21 mm 2 and estimated clock rate is about 34MHz, which satisfies most realtime applications. Since it is basically a mean squared error computation circuit, various kinds of VQ
Hierarchical mixtures of experts and the EM algorithm
, 1993
"... We present a treestructured architecture for supervised learning. The statistical model underlying the architecture is a hierarchical mixture model in which both the mixture coefficients and the mixture components are generalized linear models (GLIM’s). Learning is treated as a maximum likelihood ..."
Abstract

Cited by 885 (21 self)
 Add to MetaCart
We present a treestructured architecture for supervised learning. The statistical model underlying the architecture is a hierarchical mixture model in which both the mixture coefficients and the mixture components are generalized linear models (GLIM’s). Learning is treated as a maximum likelihood
Fusion, Propagation, and Structuring in Belief Networks
 ARTIFICIAL INTELLIGENCE
, 1986
"... Belief networks are directed acyclic graphs in which the nodes represent propositions (or variables), the arcs signify direct dependencies between the linked propositions, and the strengths of these dependencies are quantified by conditional probabilities. A network of this sort can be used to repre ..."
Abstract

Cited by 484 (8 self)
 Add to MetaCart
with the task of fusing and propagating the impacts of new information through the networks in such a way that, when equilibrium is reached, each proposition will be assigned a measure of belief consistent with the axioms of probability theory. It is shown that if the network is singly connected (e.g. treestructured
Loopy belief propagation for approximate inference: An empirical study. In:
 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 errorcorrecting codes. The most dramatic instance of this is the near Shannonlimit performanc ..."
Abstract

Cited by 676 (15 self)
 Add to MetaCart
. For each experimental run, we first gen erated random CPTs. We then sampled from the joint distribution defined by the network and clamped the observed nodes (all nodes in the bottom layer) to their sampled value. Given a structure and observations, we then ran three inference algorithms junction tree
Recursive Distributed Representations
 Artificial Intelligence
, 1990
"... A longstanding difficulty for connectionist modeling has been how to represent variablesized recursive data structures, such as trees and lists, in fixedwidth patterns. This paper presents a connectionist architecture which automatically develops compact distributed representations for such compo ..."
Abstract

Cited by 414 (9 self)
 Add to MetaCart
A longstanding difficulty for connectionist modeling has been how to represent variablesized recursive data structures, such as trees and lists, in fixedwidth patterns. This paper presents a connectionist architecture which automatically develops compact distributed representations
Performance of a TreeStructured Hierarchical Memory Multiprocessor
 Department of Computer and Information Science, The Ohio State University
, 1992
"... Latency and synchronization overheads have been identified as fundamental problems in largescale shared memory multiprocessing. In an earlier paper, one of the authors introduced a hierarchical shared memory multiprocessor architecture [9]. This architecture, based on hi erarchical shared memor ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
memory, exploits the notion of partial sharing of variables to reduce latency and synchronization costs. Using a stochastic model for generation of memory requests by each processor, a simulationbased study of the performance of the Treestructured Hierarchical Memory Multiprocessor architecture
Partial parsing via finitestate cascades
 Natural Language Engineering
, 1996
"... Finitestate cascades represent an attractive architecture for parsing unrestricted text. Deterministic parsers specified by finitestate cascades are fast and reliable. They can be extended at modest cost to construct parse trees with finite feature structures. Finally, such deterministic parsers d ..."
Abstract

Cited by 340 (4 self)
 Add to MetaCart
Finitestate cascades represent an attractive architecture for parsing unrestricted text. Deterministic parsers specified by finitestate cascades are fast and reliable. They can be extended at modest cost to construct parse trees with finite feature structures. Finally, such deterministic parsers
Mining TreeStructured Data on Multicore Systems
"... Mining frequent subtrees in a database of rooted and labeled trees is an important problem in many domains, ranging from phylogenetic analysis to biochemistry and from linguistic parsing to XML data analysis. In this work we revisit this problem and develop an architecture conscious solution targeti ..."
Abstract

Cited by 10 (0 self)
 Add to MetaCart
Mining frequent subtrees in a database of rooted and labeled trees is an important problem in many domains, ranging from phylogenetic analysis to biochemistry and from linguistic parsing to XML data analysis. In this work we revisit this problem and develop an architecture conscious solution
A Treestructured Approach to Medical Diagnosis Tasks
 ECAIWorkshop Neural Networks and Structured Knowledge
, 1996
"... A general approach for the generation of structured knowledge by integrating treestructured and connectionist mechanisms is proposed. We present our main ideas concerning the amalgamation of symbolic tree structures and topology preserving neural networks. Goals of this research are to develop a mo ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
A general approach for the generation of structured knowledge by integrating treestructured and connectionist mechanisms is proposed. We present our main ideas concerning the amalgamation of symbolic tree structures and topology preserving neural networks. Goals of this research are to develop a
An Experiment in Synchronizing Heterogeneous TreeStructured Data
, 2004
"... Increased reliance on optimistic data replication has led to burgeoning interest in tools and frameworks for synchronizing disconnected updates to replicated data. To better understand the issues underlying the design of generic and heterogeneous synchronizers, we have implemented an experimental fr ..."
Abstract
 Add to MetaCart
framework, called Harmony, that can be used to build synchronizers for treestructured data stored in a variety of concrete formats. We present Harmony’s architecture, formalize its key components (a simple core synchronization algorithm together with a set of userdefined mappings between diverse concrete
Results 1  10
of
1,035