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 164 for “"Data-Sparsity"”.
-
Parameter and Data Sparsity for Efficient Training of Large Neural Networks
… Simultaneously, the exponential growth in data volumes has compounded the challenges associated with training these expansive models. This thesis utilizes randomized algorithms to leverage the notion of dynamic sparsity, where only a small subset of parameters is crucial for each input, and …
-
Addressing training data sparsity and interpretability challenges in AI based cellular networks
… hindered by two key challenges: (i) training data is not as freely available in cellular networks as in other fields where AI has made a profound impact and (ii) current AI models tend to have black box behavior making operators reluctant to entrust the operation of multibillion mission …
-
The Unreasonable Usefulness of Approximation by Linear Combination
Through the exploitation of data-sparsity ---a catch all term for savings gained from a variety of approximations--- it is possible to reduce the computational cost of accurate electronic structure calculations to linear. Meaning, that the total time to solution for the calculation grows at the …
-
DEEP LEARNING METHODS FOR NANOPORE SIGNAL PROCESSING: ACCURATE REAL-TIME SEGMENTATION AND DNA METHYLATION DETECTION IN SPARSE REGIMES
… signals, and methylation detection under data sparsity. We introduce a convolutional framework for rapid, accurate signal segmentation, enabling accurate real-time downstream applications, alongside a comprehensive evaluation pipeline tailored to nanopore signal characteristics for …
-
Towards scalable taxi demand prediction
… across varying spatial-temporal resolutions and data conditions. Scalable taxi demand prediction refers to the capability of forecasting models to adapt to different granularities of spatial and temporal data while maintaining prediction accuracy, a critical requirement for practical urban …
-
Bayesian Nonparametric Approaches for Modelling Stochastic Temporal Events
… automatically learn the model complexity from data. In this thesis, I propose a set of Bayesian nonparametric approaches for stochastic temporal event modelling with the consideration of event similarity, interaction, occurrence time and emitted observation. Specifically, I tackle following …
-
Explainable Neural Attention Recommender Systems
… still face some realworld limitations. The data sparsity problem originates from the unprecedented variety of available items, making generated suggestions irrelevant to many users. Furthermore, many systems have been recently expected to accompany their suggestions with corresponding …
-
Context-Dependent Acoustic Modelling for Speech Recognition
… unseen in the training corpus. To address this data sparsity problem, parameter sharing/tying is widely adopted. However, this solution introduces another problem: all the CD states in the same cluster share the same set of parameters, making them indistinguishable during decoding. This problem …
-
Neural Networks for Personalized Recommender Systems
… Specifically, these challenges include: (1) data sparsity, (2) the complex relationships between users and items, (3) dynamic user preferences. To address the data sparsity, this thesis proposes to learn both collaborative features and content representations to generate recommendations in …
-
Extracting the Wisdom of Crowds From Crowdsourcing Platforms
… context—without tapping into the vast amount of data available on online crowdsourcing platforms. To extract WoC from participants on online platforms, there exist at least three challenges, including social influence, suboptimal aggregation strategies, and data sparsity. This dissertation aims …
-
Ensemble methods for top-N recommendation
… of a user to an item. Based on historical data of users, recommender systems are able to make relevant recommendations to users. Due to its usefulness, Recommender systems have been widely used in many applications, including e-commerce and healthcare information systems. However, existing …
-
From HPSG-based Persian Treebanking to Parsing
… Statistical parsers require a set of annotated data, called a treebank, to learn the grammar of a language and apply the learnt model on new, unseen data. This set of annotated data is not available for all languages, and its development is very time- consuming, tedious, and expensive. In this …
-
Advancing Responsible Recommendation Systems: Enhancing Accuracy, Diversity, and Fairness
… challenges such as the cold start problem, data sparsity, over-specialization, and lack of fairness. These limitations compromise the quality of recommendations and weaken user trust and satisfaction, potentially leading to reduced user engagement. Facing these challenges, this thesis …
-
A COMPARISON OF METHODS TO IDENTIFY INTERVENTION TARGETS TO REDUCE DISPARITIES ACROSS INTERSECTIONAL GROUPS USING CAUSAL DECOMPOSITION ANALYSIS
… evaluates three modeling strategies to address data sparsity in the context of intersectional causal decomposition: (1) fixed effects models, which include indicator variables for each group without borrowing strength; (2) Multilevel Analysis of Individual Heterogeneity and Discriminatory …
-
Out-of-distribution generalization in graph neural networks : problems, methods and applications
… most natural representations of many real-world data, such as social networks, chemical molecules, and transportation networks. Graph neural networks (GNNs) are deep neural networks (DNNs) that are specially designed for graphs and have aroused great research interest. Recently, GNNs have been …
-
Predictive spatio-temporal modelling with neural networks
… complex non-linear spatio-temporal dependencies, data sparsity and uncertainty. Hongbin Liu investigated the modelling difficulties and proposed three novel models to tackle the difficulties for three common spatio-temporal datasets. He also conducted extensive experiments on several real-world …
-
Causal Preference Inference in Reinforcement Learning-Based Recommender System
… these systems face several challenges, including data sparsity, high-dimensional and noisy state representations, and difficulties in estimating causal effects, particularly in offline RL settings. This dissertation explores these challenges and employs different methods in causal inference to …
-
Integration of spatial data context into machine learning models
… has accumulated a large volume of spatial data from various resources like seismic surveys, well logs and production information, which provide a huge potential for data analytics and machine learning application to assist physics-based models. The ongoing digitalization transformation in …
-
Better document-level natural language understanding through data-driven applications of discourse theories
… models, is the lack of available gold-standard data, caused by the tedious and expensive human annotation process. To overcome the prevalent data sparsity issue in the areas of discourse analysis and discourse parsing, it is imperative to find new methods to generate large-scale and high-quality …
-
Cross domain recommender systems using matrix and tensor factorization
Today, the amount and importance of available data on the internet are growing exponentially. These digital data has become a primary source of information and the people’s life bonded to them tightly. The data comes in diverse shapes and from various resources and users utilize them in almost all …
Page 1 of 9