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 155 for “"Catastrophic Forgetting"”.
-
Catastrophic Forgetting in Language Models
Catastrophic forgetting remains a persistent challenge in the continual learning paradigm of neural networks, particularly in the context of pre-trained language models. This thesis investigates the phenomenon of catastrophic forgetting in large language models (LLMs), with a focus on BERT, through …
-
Overcoming catastrophic forgetting in heterogeneous federated learning
… patient privacy. However, key challenges such as catastrophic forgetting and local overfitting hinder the effectiveness of FL models in heterogeneous healthcare environments. This thesis addresses these challenges through two complementary studies. The first study introduces Federated Impressions, …
-
Reducing Catastrophic Forgetting in Self-Organizing Maps
… from new data samples. This problem is known as catastrophic forgetting and remains an unsolved problem in the domain of machine learning to this day. To overcome catastrophic forgetting, different approaches have been proposed. One major line of thought advocates the use of memory buffers to …
-
New Insights on Catastrophic Forgetting in Neural Networks
… adaptation of new information while combating catastrophic forgetting, \textit{i.e.} stability-plasticity dilemma. This thesis is comprised of four major chapters that explore different aspects of continual learning and propose novel solutions to address some of its challenges. First, we …
-
Deep learning methods for mitigating catastrophic forgetting in medical imaging
… time. A persistent challenge in this field is catastrophic forgetting, where models overwrite past knowledge when learning new tasks, limiting their practical use in dynamic environments. This thesis introduces a new framework called CLFCR-MC (Continual Learning Framework with Contrastive …
-
Neuron Clustering for Mitigating Catastrophic Forgetting in Supervised and Reinforcement Learning
… in more realistic online environments is that of catastrophic forgetting. Catastrophic forgetting affects supervised learning systems when input samples are temporally correlated or are non-stationary. However, most real-world problems are non-stationary in nature, resulting in prolonged periods …
-
Referencing Unlabelled World Data to Prevent Catastrophic Forgetting in Class-incremental Learning
… a novel strategy to address the challenge of "catastrophic forgetting" in deep continual-learning systems. The term refers to severe performance degradation for older tasks, as a system learns new tasks that are presented sequentially. Most previous techniques have emphasized preservation of …
-
Beyond catastrophic forgetting : advancing continual learning for robust and fair medical image analysis
… models to learn sequentially while addressing catastrophic forgetting. However, challenges remain in resource efficiency, generalization, adaptation, fairness and the inefficient integration of pretrained models, especially in medical image analysis. To tackle these challenges, this …
-
The Impact Of Experience Replay Buffers On Catastrophic Forgetting Within Proximal Policy Optimization
Catastrophic Forgetting continues to be a prevalent issue for any neural-based approach to learning. Without better understanding and solutions to solving catastrophic forgetting, learning performance and efficacy in autonomous agents, particularly deep learning-based agents will become drastically …
-
Developing Generative Adversarial Networks for Classification and Clustering: Overcoming Class Imbalance and Catastrophic Forgetting
… network is introduced to handle the catastrophic forgetting of past tasks. As the job grows, the network structure of ACL also grows simultaneously. Therefore, ACL is not scalable. We propose an online Scalable Adversarial Continual Learning (SCALE) framework where the parameter …
-
Learning with Distribution Shift: Theory and Practice
… in static environments, they suffer from \emph{catastrophic forgetting} in CL scenarios - a phenomenon where performance on earlier tasks deteriorates after learning new ones. Although significant efforts have been devoted to developing practical CL algorithms, the theoretical understanding of …
-
Brain-Inspired Continual Learning: Rethinking the Role of Features in the Stability-Plasticity Dilemma
… existing approaches to CL face the challenge of catastrophic forgetting, which occurs when a model's performance on previously learned tasks declines after learning the new task. In this dissertation, we focus on the crucial role of input data features in determining the robustness of CL models …
-
Deep Convolutional Spiking Neural Networks for Image Classification
… our network are also explored. We also studied catastrophic forgetting and its effect on spiking neural networks (SNNs). For the experiments regarding catastrophic forgetting, in the classification sections of the network we use a modified synaptic intelligence that we refer to as cost per …
-
Fast and Sustainable Video Anomaly Detection with Continual Learning
… under these conditions and may suffer catastrophic forgetting when adapting to new environments. This thesis proposes RegiGrow, a parameter-efficient continual adaptation framework built on the Flashback retrieval pipeline. RegiGrow integrates Mixture-of-Experts Low-Rank Adaptation into …
-
Advanced continual machine learning
Deep learning suffers from catastrophic forgetting when learning a dynamic environment, where the data is continuously gathered. This thesis is proposed to tackle the catastrophic forgetting problem under various settings and constraints, i.e., rehearsal-based, rehearsal-free, data scarcity, …
-
Multi-Task Reinforcement Learning: From Single-Agent to Multi-Agent Systems
… multi-task learning due to a phenomenon known as catastrophic forgetting. In this thesis, we present a set of simulation environments for exploring the abilities of multi-task drone systems and provide a platform for testing agents in incremental single-agent and multi-agent learning scenarios. …
-
Mitigation of Catastrophic Interference in Neural Networks and Ensembles using a Fixed Expansion Layer
<p>Catastrophic forgetting (also known in the literature as catastrophic interference) is the phenomenon by which learning systems exhibit a severe exponential loss of learned information when exposed to relatively small amounts of new training data. This loss of information is not caused by …
-
Lifelong Machine Learning With Adaptive Resonance Theory
… with the mitigation of the phenomenon of catastrophic forgetting whereby learning agents that are faced with incrementally novel information deleteriously overwrite previous knowledge if that learning process is not regularized to counteract this consequence. ART algorithms solve this …
-
Towards efficient deep learning for computer vision
… issue with deep neural networks is catastrophic forgetting when encountering new or evolving tasks in a sequential manner. The model must be retrained with all the data or tasks encountered to avoid forgetting, thus making them unsuitable for many real-world applications. The second …
Page 1 of 8