Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 64 for “"Pruning techniques"”.
-
An Anomaly Detection System based on Ensemble of Detectors with Effective Pruning Techniques
… now available. To this end, anomaly detection techniques rely on machine learning techniques to model the normal behaviour of the system. This model is used as a baseline for the detection of anomalies during system operation. The problem is that there is no one machine learning technique that …
-
On forward pruning in game-tree search
… and practical applications of forward pruning in game-tree search, also known as selective search. Our research focuses on three main areas: (1) Solving Tigers and Goats - using forward pruning techniques in addition to other advanced search techniques to prove that Tigers and Goats is …
-
Syntactic Sentence Compression for Text Summarization
… our work on sentence compression using syntactic pruning methods in order to improve automatic text summarization. Sentence compression has several applications in Natural Language Processing such as text simplification, topic and subtitle generation, removal of redundant information and text …
-
A Linear Delay Algorithm for Enumerating All Connected Induced Subgraphs
… Pattern-mining-based graph learning and analysis techniques report meaningful biological subnetworks that elucidate important interactions among entities. At the backbone of these algorithms is the enumeration of pattern space. In this work, we propose an efficient algorithm for enumerating all …
-
Explainable deep learning for image understanding
… supervised segmentation guided by attributes, pruning techniques to enhance model interpretability, and a framework for 3D editing informed by visual explanations. These advancements boost model trust across diverse applications.
-
Optimal Task Scheduling on Parallel Systems
… optimal schedule. The applicability of existing pruning techniques used on A* are re-investigated and new pruning techniques to further speedup the memory limited A*algorithms are proposed. The first part of the work proposes MILP solutions that use problem specific knowledge to eliminate the …
-
Efficient processing of spatial queries over uncertain database
… by utilizing two uncertain object indexing techniques. To effectively support uncertain objects with a large number of instances, we further develop randomized algorithms with accuracy guarantee. Secondly, we study the problem of top k dominating query on uncertain data, which is an …
-
Maintaining the utility of learned knowledge using model-based adaptive control
… greater than that attained by popular pruning techniques. The similarity in performance responses suggests a parameterized model relating performance to the amount of learned knowledge. Given this model, a model-based adaptive control (MBAC) approach can be used to update the model …
-
ReviewMiner: An Unsupervised Method of Aspect Extraction and Aspect Rating from Product Reviews
… employs a series of heuristic strategies and pruning techniques. Experimental results have demonstrated the effectiveness of the proposed techniques and shown their advantages over comparative baselines.
-
A Multi-Objective Autotuning Framework for the Java Virtual Machine
… size of the search space machine-learning based pruning techniques are used. Evaluation on recommender system workloads show that significant improvements in both performance and power can be gained by fine-tuning JVM runitme parameters.
-
Usando permutation based indexing na detecção de plágio
… this work will create variations on existing pruning techniques, based on a "pruning" of pivots, which removes pivots that do not have much influence on a given query.
-
A pruning algorithm for one player games with hidden information
… is the description and analysis of a new pruning technique, called information set pruning, that is specific to hidden information games. Second, the One-Player Pruning Algorithm (OPPA) is presented; it is a natural and important extension of the existing One-Player Algorithm to search …
-
Changepoint detection for acoustic sensing signals
… a given multivariate series. Consideration of pruning techniques suggests that these are not practically viable for this setting. We therefore introduce approximations which vastly improve computational speed with negligible detrimental impact on accuracy. This approximated procedure is applied …
-
Influence of spacing and artificial pruning on the production of clearwood of Douglas-fir
… quality wood a review of spacing and artificial pruning techniques was made. Their effects on wood quality were also studied. Results of research conducted at the U.B.C. Research Forest and at Wind River, U.S.A. in the Gifford Pinchot National Forest are presented in order to define some …
-
Empowering Emotional Support Chatbots with Large Language Models
… ChatGPT. Through the application of fine-tuning techniques on newer datasets, this research endeavors to explore the inherent capabilities of language models in delivering nuanced emotional support across diverse scenarios. Central to its objectives is the refinement of emotional support chatbots …
-
Constraint-based Mining of Frequent Arrangements of Temporal Intervals
… prefix-based. The above methods apply efficient pruning techniques that include a set of constraints consisting of regular expressions and gap constraints that add user-controlled focus into the mining process. Moreover, based on the extracted patterns a standard method for mining association …
-
LoFT: Finding Lottery Tickets through Filter-wise Training
Recent work on pruning techniques and the Lottery Ticket Hypothesis (LTH) shows that there exist “winning tickets” in large neural networks. These tickets represent versions of the full model that can be trained separately to achieve comparable accuracy with respect to the full models. However, in …
-
GENERATING PLANS IN CONCURRENT, PROBABILISTIC, OVER-SUBSCRIBED DOMAINS
… domain independent heuristic functions and pruning techniques were developed. The key ideas are to exploit dominance relations for candidate action sets and to develop relaxed planning graphs to estimate the expected rewards of states. This thesis contributes (1) an AO* based planner to …
-
Advancing efficiency and trustworthiness : from computer vision to multimodal large language models
… dimensions simultaneously. First, we explore techniques for neural network efficiency through pruning and quantization. We introduce mixed-precision quantization tickets that unify pruning and quantization paradigms, and develop sparse cocktail training to produce multiple sparse subnetworks …
Page 1 of 4