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 1264 for “"Generalisation"”.
-
Domain Generalisation in Reinforcement Learning
… rudimentary input patterns leading to a lack of generalisation. Common approaches to remedy their problems are to (1) obtain larger datasets for better data coverage, (2) train neural networks with more parameters, or (3) include more input variations either by simply adding them to the training …
-
A generalisation of property "R"
Nous étudions un problème de chirurgie de Dehn, à savoir la caractérisation des nœuds dans les espaces lenticulaires qui admettent des chirurgies intégrales homéomorphes à S1 x S2. Nous montrons que ces nœuds sont fibrés et qu'ils bordent des surfaces de Seifert planaires. De façon équivalente, les …
-
Combinatorial Generalisation in Machine Vision
The human capacity for generalisation, i.e. the fact that we are able to successfully perform a familiar task in novel contexts, is one of the hallmarks of our intelligent behaviour. But what mechanisms enable this capacity that is at the same time so impressive but comes so naturally to us? This …
-
Randomised numerical schemes : generalisation and applications
This thesis focuses on the theoretical analysis, numerical implementation, and practical applications of randomized numerical schemes for solving differential equations characterized by low regularity and temporal irregularities. Randomized schemes, which introduce stochastic perturbations into …
-
Generalisation and optimisation in neural networks
… thesis is to contribute to our understanding of generalisation and optimisation in neural networks. We ask the following questions: <br>1. Why can highly expressive neural networks learn functions that generalise? <br>2. Optimiser hyperparameters can significantly affect generalisation. Why? How …
-
Symmetry and generalisation in machine learning
… the impact of invariance and equivariance on generalisation in supervised learning. We use the perspective afforded by an averaging operator to show that for any predictor that is not equivariant, there is an equivariant predictor with strictly lower test risk on all regression problems where …
-
G2G - From Data Generation to Model Generalisation
… quality, or annotations. Understanding generalisation therefore requires considering not only architectural choices but also the ways in which data is generated, structured, and presented. While much research has focused on developing more complex networks or regularisation schemes, this …
-
Graph Neural Networks: From Expressivity to Generalisation
… graph representation learning: expressivity and generalisation. Expressivity refers to a model's ability to approximate functions on graphs, while generalisation measures its capacity to adapt to unseen data. We address challenges in both paradigms by designing efficient and powerful models and …
-
Barriers to generalisation in acoustic hive monitoring
… to characterise the major barriers to cross-hive generalisation.<br><br>In Chapter 2, I develop a pipeline to extract handcrafted and deep-learned features from honeybee audio samples and train neural networks for binary classification. Using a dataset of 10 queenless and queenright hives, I test …
-
Temporal abstraction and generalisation in reinforcement learning
… of artificial intelligence systems. The generalisation test examines an agent's ability to reason over the world in an \emph{abstract} manner. In reinforcement learning problem settings, where an agent interacts continually with the environment, multiple notions of abstraction are …
-
Processes underlying generalisation of conditioning in humans
… aimed to investigate the processes underlying generalisation of conditioning in humans. Dominant associative accounts of generalisation predict that learning generalises on the basis of shared stimulus elements, and is therefore strongest to novel stimuli which are highly similar to the trained …
-
Cartographic knowledge-based generalisation of spatial features
This study has developed a framework for generalisation of geographical features using a knowledge-based solution. The proposed method consists of three major components: • Generalisation Framework - a detailed generalisation framework for deriving multi-scale spatial data has been developed based …
-
Constructive neural networks : generalisation, convergence and architectures
… classify future data. This is known as generalisation. A more practical aspect of pattern recognition methods is how quickly they can be trained and how reliably a good solution is found. Feedforward neural networks have been shown to provide good generali- sation on a variety of …
-
Semigroups have layers: a generalisation of stratified semigroups
… As these semigroups can be viewed as a generalisation of regular semigroups, our approach aims to adapt methods used to understand regular semigroups to the E−dense setting. Our first method is a geometric approach inspired by work due to K. S. S. Nambooripad, while the second is based …
-
Inductive biases and generalisation for deep reinforcement learning
<p>In this thesis we aim to improve generalisation in deep reinforcement learning. Generalisation is a fundamental challenge for any type of learning, determining how acquired knowledge can be transferred to new, previously unseen situations. We focus on reinforcement learning, a framework …
-
Generalisation and expressiveness for over-parameterised neural networks
… two fundamental properties: expressive power and generalisation capability. The former refers to the model's ability to fit a large variety of data sets, while the latter enables the network to extrapolate patterns from training examples and apply them to previously unseen data. This thesis …
-
A model of functional creativity for generalisation enhancement
… functional creativity as a mechanism for generalisation in reinforcement learning. Its main proposal is that agents can adapt to novel tasks by recomposing structured representations of past experience, rather than relying on reactive policies or overfitting pattern interpolation. Inspired …
-
Enhancement of Model Generalisation in Multiobjective Genetic Programming
… learning area. We aim to improve the model generalisation of MOGP in both regression and classification tasks. The work in this thesis has three main contributions. First, we propose replacing the division operator used in genetic programming with an analytic quotient (AQ) operator in …
Page 1 of 64