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 268 for “"Continual Learning"”.

  1. TOWARDS PRACTICAL CONTINUAL LEARNING

    Continual learning enables models to acquire new knowledge over time while retaining previously learned capabilities. While existing research largely focuses on mitigating catastrophic forgetting, practical continual learning also requires adaptability, generalizability, robustness, and efficiency. …

    nus Repository record for TOWARDS PRACTICAL CONTINUAL LEARNING (opens in a new tab) Download file for TOWARDS PRACTICAL CONTINUAL LEARNING (opens in a new tab)

  2. ADVERSARY AWARE CONTINUAL LEARNING

    Continual learning approaches are useful as they help the model to learn new information (classes) sequentially, while also retaining the previously acquired information (classes). However, these approaches are adversary agnostic, i.e., they do not consider the possibility of malicious attacks. In …

    rowan Repository record for ADVERSARY AWARE CONTINUAL LEARNING (opens in a new tab)

  3. Continual Learning for Classification Tasks

    The traditional machine learning models can only learn from stationary data stream and are very vulnerable to the changing environment. To encourage the machine learners to be more human-like and practical in the real-world, continual learning was put forward and attracts a surge of attention in …

    carleton Repository record for Continual Learning for Classification Tasks (opens in a new tab)

  4. Continual Learning with Sketched Structural Regularization

    Preventing catastrophic forgetting while continually learning new tasks is an essential problem in continual learning. Structural regularization (SR) refers to a family of algorithms that mitigate catastrophic forgetting by penalizing the network for changing its "critical parameters" from previous …

    jhu Repository record for Continual Learning with Sketched Structural Regularization (opens in a new tab)

  5. Asymmetric Clustering in Federated Continual Learning

    … under-explored challenge in Clustered Federated Learning (CFL). Existing methods often compromise data utilization or model accuracy by either separating devices with different data quality into distinct clusters or merging all devices into a single cluster. The need for asymmetric clustering …

    waterloo Repository record for Asymmetric Clustering in Federated Continual Learning (opens in a new tab)

  6. Continual learning-based Video Object Segmentation

    Machine learning models, specifically deep convolutional neural networks, have exceeded human-level performance in many research areas, such as object classification and voice recognition. However, they are not comparable to humans in real-world learning scenarios when the training data is …

    waterloo Repository record for Continual learning-based Video Object Segmentation (opens in a new tab)

  7. Continual Learning in Neural Machine Translation

    [ES] La traducción automática neuronal (NMT) se enfrenta a importantes retos a la hora de adaptarse a la naturaleza siempre cambiante del lenguaje natural. Los modelos tradicionales de traducción tienen dificultades para integrar nuevos términos en sus vocabularios y son propensos a olvidar la …

    upv Repository record for Continual Learning in Neural Machine Translation (opens in a new tab)

  8. Continual learning for efficient machine learning

    <p>Deep learning has enjoyed tremendous success over the last decade, but the training of practically useful deep models remains highly inefficient both in terms of the number of weight updates and training samples. To address one aspect of these issues, this thesis studies the continual learning …

    oxford Repository record for Continual learning for efficient machine learning (opens in a new tab)

  9. Efficient Continual Learning: Approaches and Measures

    … system size and computational cost. Continual learning is a research topic for dealing<br/>with such scenarios. The main challenge of continual learning is catastrophic forgetting: when<br/>training a model by sequential tasks, the model tends to forget previously learned tasks …

    bristol Repository record for Efficient Continual Learning: Approaches and Measures (opens in a new tab) Download PDF for Efficient Continual Learning: Approaches and Measures (opens in a new tab)

  10. 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 …

    vt Repository record for Continual Learning for Deep Dense Prediction (opens in a new tab)

  11. Safety-Oriented Stability Biases for Continual Learning

    Continual learning is often confounded by “catastrophic forgetting” that prevents neural networks from learning tasks sequentially. In the case of real world classification systems that are safety-validated prior to deployment, it is essential to ensure that validated knowledge is retained. We …

    waterloo Repository record for Safety-Oriented Stability Biases for Continual Learning (opens in a new tab)

  12. Continual Learning and Forgetting in Deep Learning Models

    Continual learning is a framework of learning in which we aim to move beyond the limitations of standard isolated optimization of deep learning models toward a more intelligent setting, where models or agents are able to accumulate skills and knowledge, across diverse tasks and over extended …

    waterloo Repository record for Continual Learning and Forgetting in Deep Learning Models (opens in a new tab)

  13. Continual learning from stationary and non-stationary data

    Continual learning aims at developing models that are capable of working on constantly evolving problems over a long-time horizon. In such environments, we can distinguish three essential aspects of training and maintaining machine learning models - incorporating new knowledge, retaining it and …

    vcu Repository record for Continual learning from stationary and non-stationary data (opens in a new tab)

  14. Unsupervised Progressive and Continual Learning of Disentangled Representations

    Unsupervised representation learning is an important task in machine learning that identifies and models underlying explanatory factors hidden in the observed data. In recent years, unsupervised representation learning has been attracting increasing attention for its abilities to improve …

    rit Repository record for Unsupervised Progressive and Continual Learning of Disentangled Representations (opens in a new tab)

  15. Unsupervised learning and continual learning in neural networks

    … in previous batches, which is an impediment to continual learning. Furthermore, associations need to be made explicit via paired input-target samples for the trained network to achieve its best performance on desired tasks; when the network is trained in an unsupervised manner without explicit …

    oxford Repository record for Unsupervised learning and continual learning in neural networks (opens in a new tab)

Page 1 of 14