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 8 of 8 for “"Online Continual Learning"”.
-
Adaptations of rehearsal methods for online continual learning
… automation. These systems rely heavily on deep learning models to perform complex tasks; however, the training and continual updating of such models demand substantial computational resources and storage capabilities. This introduces challenges related to cost, scalability, and sustainability, …
-
Scalable continual deep learning with computational cost considerations
<p>Continual Learning (CL) is a emerging field that focuses on developing models capable of learning continuously from a incoming stream of data, as opposed to hundreds of passes over static, curated datasets. These models aim to retain previously acquired knowledge while seamlessly integrating new …
-
Efficient robot learning for perception and mapping
… mapping and localization. In recent years, deep learning techniques have been a key enabler for many performance improvements observed in robotic systems. However, a major limitation of conventional learning-based approaches is their critical reliance on human supervision. In particular, these …
-
Mitigating the challenges of distribution shift under strong computational constraints
… under strong computational constraints in deep learning vision tasks. Through a series of contributions, it demonstrates the effectiveness of unsupervised learning in enabling efficient and adaptable models suitable for resource-constrained environments. The Diversified Dynamic Routing (DivDR) …
-
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 …
-
Towards the Safety and Robustness of Deep Models
… and object detection. Representation learning stands as a pivotal element in the efficacy of DNNs, involving the extraction of significant features from data through mechanisms like convolutional neural networks (CNNs) applied to image data. In real-world applications, ensuring the …
-
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 …
-
Lifelong Learning in Spiking Neural Networks Through Neural Plasticity
Lifelong learning, the ability to learn from continually changing data distributions in real-time, is a significant challenge in artificial intelligence. The central issue is that new learning tends to interfere with previously acquired memories, a phenomenon known as catastrophic forgetting. …