A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
Threat Stacks to Guide Pruning and Search Extensions in Shogi
[chapter]
2003
IFIP Advances in Information and Communication Technology
Preserved Fulltext
In this paper we propose to store the game-specific knowledge into threat stacks and use general rules regarding the content of these threat stacks for pruning and extension decisions. ...
To produce a reasonable move at each iteration a combination of pruning techniques and search extensions is used. ...
We explain how threat stacks can be used to make pruning and extension decisions and show how they can reduce the horizon problem. ...
doi:10.1007/978-0-387-35660-0_9
fatcat:hejlfch4ardqbk2jtgagqqhzvm
Start-synchronous search for large vocabulary continuous speech recognition
1999
IEEE Transactions on Speech and Audio Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2003; you can also visit the original URL.
The file type is application/pdf.
Index Terms-Hidden Markov model, large vocabulary continuous speech recognition, phone deactivation pruning, search, stack decoding. Steve Renals (M'91) received the B. ...
pruning-a highly efficient method of reducing the required computation. ...
ACKNOWLEDGMENT The authors are grateful to T. Robinson, with whom they have had many insightful conversations about the work reported here. ...
doi:10.1109/89.784107
fatcat:f36t6hca4jbznpicrrt2ugbeoa
Hierarchical Action Classification with Network Pruning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We propose, however, to better utilize auxiliary mechanisms, including hierarchical classification, network pruning, and skeleton-based preprocessing, to boost the model robustness and performance. ...
We also analyze our method with extensive comparisons and ablation studies. ...
For future work, we would like to incorporate outdoor datasets or datasets obtained from the Internet, such as the Kinetics dataset [38] . ...
arXiv:2007.15244v1
fatcat:yeou2bovkjdfpp34g525fvdoji
Lightweight Architecture for Real-Time Hand Pose Estimation with Deep Supervision
2019
Symmetry
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Our architecture is essentially a deeply-supervised pruned network in which less important layers and branches are removed to achieve a higher real-time inference target on resource-constrained devices ...
We further make deployment optimization to facilitate the parallel execution capability of central processing units (CPUs). ...
Implementation Details In stack pruning, we cut off the second network stack without any training process. In level pruning, we add three supervision modules and retrain the one stack network. ...
doi:10.3390/sym11040585
fatcat:v4xpfaqr2rbkre52mrww4y3qye
Parallel interval-Newton using message passing
2001
Proceedings of the 2001 ACM/IEEE conference on Supercomputing (CDROM) - Supercomputing '01
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2004; you can also visit the original URL.
The file type is application/pdf.
For unconstrained problems, solve for stationary points For constrained problems, solve for KKT points (or more generally for Fritz-John points) Add an additional pruning condition: -Compute interval extension ...
Otherwise, bisect the intersection and apply root inclusion test to each resulting subinterval. µ This is a branch-and-prune (BP) scheme. ...
doi:10.1145/582034.582057
dblp:conf/sc/GauS01
fatcat:jp2sryko2zgxbgzgcg4xbvf2sy
Complexity-Adjustable SC Decoding of Polar Codes for Energy Consumption Reduction
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In addition, a logarithmic likelihood ratio (LLR)-threshold based path extension scheme is designed to further reduce the memory consumption of stack decoding. ...
This paper proposes an enhanced list-aided successive cancellation stack (ELSCS) decoding algorithm with adjustable decoding complexity. ...
Because low SNR leads to small |E[Li ]|,
for an extension stage in ELSCS doubles while the average less pruning will happen and the correct path is more likely
number of extension stages required ...
arXiv:1912.07649v1
fatcat:7axwp3yvana3hde7kmm7xq42xm
Reproducing concurrency failures from crash stacks
2017
Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering - ESEC/FSE 2017
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
ConCrash efficiently explores the huge space of possible test codes to identify a failure-inducing one by using a suitable set of search pruning strategies. ...
In this paper, we present ConCrash, a technique to automatically generate test codes that reproduce concurrency failures that violate thread-safety from crash stacks, which commonly summarize the conditions ...
PS-Stack is particularly effective when only few executions reach the POF under the calling context specified in the crash stack trace (CST), as it prunes all those test codes that fail to do so. ...
doi:10.1145/3106237.3106292
dblp:conf/sigsoft/BianchiPT17
fatcat:whyqgvtorffi7e7h3zkilncpx4
Approximate Pruning in Tabled Logic Programming
[chapter]
2003
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
In this paper we present an extension to the evaluation mechanism of Tabled Prolog to support pruning. This extension builds on the concept of demand to select tables to prune. ...
Pruning provides an important tool for control of nondeterminism in Prolog systems. ...
In this paper we present an extension to the evaluation mechanism of Tabled Prolog to support pruning. This extension builds on the concept of demand [9] to select tables to prune. ...
doi:10.1007/3-540-36575-3_6
fatcat:7p64epoab5dr5k6knkvplwezpy
An efficient A* stack decoder algorithm for continuous speech recognition with a stochastic language model
1992
[Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2005; you can also visit the original URL.
The file type is application/pdf.
The stack decoder is an attractive algorithm for controlling the acoustic and language model matching in a continuous speech recognizer. ...
The resultant algorithm is not admissible, but has been demonstrated to have a low probability of search error and to be very efficient. ...
Thus by comparison, only theories that dominate the lubsf need be retained on the stack and the stack pruning threshold can be set to zero for top-1 recognition. ...
doi:10.1109/icassp.1992.225981
dblp:conf/icassp/Paul92
fatcat:kr6pvbo6qvenlhsfiwvd67dmfu
Automatic Induction of Neural Network Decision Tree Algorithms
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This construction can be used to transfer weights when growing or pruning a decision tree, allowing non-greedy decision tree algorithms to automatically learn and adapt to the ideal architecture. ...
This work presents an approach to automatically induction for non-greedy decision trees constructed from neural network architecture. ...
The routing layer determines whether nodes are to be pruned or grafted. The decision to prune or graft a node was done through p(x t+1 |x t , θ). ...
arXiv:1811.10735v4
fatcat:brmk4hmxhrhjndqeunqr4temnq
Compact Neural Networks via Stacking Designed Basic Units
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
By contrast, structured pruning can help eliminate this drawback but it requires complex criterion to determine which components to be pruned. ...
Given the basic units of various architectures, they are combined and stacked in a certain form to build up compact neural networks. ...
Existing pruning method can be roughly divided into unstructured pruning and structure pruning in terms of the types of network components to be pruned. ...
arXiv:2205.01508v1
fatcat:uqhxhwqek5gmdgegg5wemwc4zi
Algorithms for an optimal A* search and linearizing the search in the stack decoder
1991
[Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2006; you can also visit the original URL.
The file type is application/pdf.
This paper describes a method for performing the optimal A* search which guarantees to find the most likely path (recognized sentence) while extending the minimum number of stack entries. ...
It implements a best-first tree search of the language to find the best match to both the language model and the observed speech. ...
To minimize these problems, a pruning threshold can be applied to the stack insertion operations and the secondary heap generation. ...
doi:10.1109/icassp.1991.150434
dblp:conf/icassp/Paul91a
fatcat:zn35ogpnmfdwxht2gqa5lzxbji
Retroactive Subsumption-Based Tabled Evaluation of Logic Programs
[chapter]
2010
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Tabling based systems use call similarity to determine if a tabled subgoal will produce their own answers or if it will consume from another subgoal. ...
In this work, we present an extension, named Retroactive Call Subsumption, that supports call subsumption by allowing full sharing of answers between subsumed/subsuming subgoals, independently on the order ...
Once reactivated, the subgoal frame for the pruned generator is pushed again into the top of the subgoal frame stack and its state altered to evaluating. ...
doi:10.1007/978-3-642-15675-5_13
fatcat:paebhxy67rakhj2h2ppujtph24
Stacked indexed views in microsoft SQL server
2005
Proceedings of the 2005 ACM SIGMOD international conference on Management of data - SIGMOD '05
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf.
To support view matching for stacked views, a signature mechanism was added to the optimizer. ...
View stacking (also called views on views) relaxes one restriction by allowing a materialized view to reference both base tables and other materialized views. ...
A natural extension of SPJG views is to allow some or all of the source tables in a view definition to be other materialized views, rather than to base tables. ...
doi:10.1145/1066157.1066179
dblp:conf/sigmod/DeHaanLZ05
fatcat:53gmouan7jhcholqqijfbblcrq
METEORs: High Performance Theorem Provers using Model Elimination
[chapter]
1991
Automated Reasoning Series
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
If a reduction or unit extension does not specialize any variables, no bindings will be trailed and a simple check of whether the top of the trail stack has changed is sufficient to determine whether pruning ...
The most useful of these prunes (with failure) a branch of the search tree if the goal (literal eligible for extension and reduction) is identical to an ancestor literal. ...
doi:10.1007/978-94-011-3488-0_2
fatcat:x7yc6muwnvg6rj3ruvbgwe6tze
« Previous
Showing results 1 — 15 out of 17,872 results