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 55 for “"Continual learning"”.
-
Continual Learning for Affective Robotics
… human socio-emotional behaviours while also learning to respond in a manner that fosters their social and emotional wellbeing. Embedding affective robots with learning mechanisms that enable such a robust understanding of human behaviour as well as their own role in an interaction forms the …
-
Probabilistic Continual Learning using Neural Networks
… passes through the data. However, standard deep-learning techniques are unable to continually adapt as the environment changes: either they forget old data or they fail to sufficiently adapt to new data. This limitation is a major barrier to applications in many real-world settings, where the …
-
Continual Learning for Deep Dense Prediction
Transferring a deep learning model from old tasks to a new one is known to suffer from the catastrophic forgetting effects. Such forgetting mechanism is problematic as it does not allow us to accumulate knowledge sequentially and requires retaining and retraining on all the training data. Existing …
-
Continual Learning of Object Classification in the Real World
Technological advances in deep learning have brought remarkable performance in the object classification task but only when all the training data of classes to be learned are available at the same time. However, real-world data continually evolve through time, resulting in ever-changing learning …
-
Paradigmi ispirati da scienze neurocognitive per il Continual Learning
… a differenti contesti ed esperienze. Il Continual Learning, (CL) è un paradigma della IA che si concentra sull'abilità dei modelli di apprendere in maniera continuata nel tempo, acquisendo nuova conoscenza e, al tempo stesso, mantenendo e ampliando le informazioni precedentemente …
-
MACON: memory-augmented continual learning for open-world classification
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms
-
Tree-based Data Replay for More Efficient LLM Continual Learning
… designed to enhance the efficiency of LLMs’ continual training. It leverages the evolutionary relationships among domain-specific data to inform the replay strategy, selectively excluding similar data from the training of current subdomains to optimize efficiency. Initial experiments …
-
Beyond pre-training: continual learning and hallucinations in transformer-based language models.
… over a period of time, requiring models to continually learn on newly acquired data. The research investigates existing approaches to continual learning and identifies a gap in how impact to previous domains/tasks is determined without access to the data. Based on this, a novel method is …
-
Efficient Continual Learning and On-Device Training for Mobile and IoT Devices
… and computational power. However, achieving continual learning (CL) and on-device training on resource-constrained edge devices poses significant challenges, both in terms of resource limitations and the complexity of learning algorithms to continually learn new tasks without forgetting old …
-
Continual Learning for Engineering: Benchmarking and Exploring Strategies for 3D Engineering Problems
Engineering applications of machine learning often involve high-dimensional, computationally intensive simulations paired with limited and evolving datasets. As new designs and constraints emerge, models must adapt to incoming data without frequent retraining, which is often infeasible due to the …
-
Requirements engineering-driven collaborative software maintenance framework for embedded systems using continual learning
… failure detection in the maintenance phase with continual learning as a mechanism of incremental inclusion. The novel CNNBiLSTM deep-learning model on a public drone dataset outperformed state-of-the-art models, achieving a 100% true positive rate in three scenarios. On the other hand, we …
-
Enhancing multi-label object recognition in complex images via region-based continual learning
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms
-
Advanced adaptive classifier methods for data streams
… influx of big data. However, traditional batch learning models face significant obstacles in effectively learning from these vast and constantly evolving data streams and generating up-to-date outcomes. To overcome these limitations, Stream Learning (SL) has emerged as a promising solution that …
-
Efficient Knowledge Transfer and Adaptation for Speech and Beyond
… to address the limitations of transfer learning in dynamically evolving audio and speech processing contexts, particularly through novel approaches for class-incremental learning, parameter-efficient adaptation, and multimodal modeling. First, we provide a comprehensive framework for …
-
Determining Conditions That Enable or Impede the Inclusion of Climate Justice in Municipal Adaptation Planning in Canada
… leadership, process design, worldview, and continual learning are the insertion points at which justice can be included or excluded. Furthermore, integrating climate justice requires an iterative process of evolving values which influence and could continually improve the process structure.
-
Self-supervised learning for data-efficient human activity recognition
… actions. Motivated by advancements in deep learning, human activity recognition research has also widely adopted these methods. However, compared to other data modalities, human activity recognition models struggle with the limited availability of labels, due to the difficulty of …
-
Referencing Unlabelled World Data to Prevent Catastrophic Forgetting in Class-incremental Learning
… 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 existing knowledge while learning …
-
Towards Trustworthy Learning in Temporal Learning Environments
… thesis explores how to build trustworthy machine learning systems that learn and adapt over time. As machine learning moves beyond static benchmarks and into real-world settings, where data distributions shift, environments change, and objectives evolve, it is more important and difficult to …
-
Self-supervised Learning Methods for Vision-based Tasks
… to leverage this data for training many machine learning models. Among them, self-supervised learning appears as an efficient solution capable of training powerful and generalizable models. More specifically, instead of relying on human-generated labels, it proposes training objectives that use …
-
MODEL ADAPTATION FOR EDGE AI
… We introduce Chameleon, an energy-efficient continual learning framework. Secondly, generic DNN models can lead to wasteful and inefficient inference. We propose CRISP, a class-aware pruning framework that employs a hybrid structured sparsity pattern. Thirdly, while low-precision integer …
Page 1 of 3