Overfitting and the presence of noisy labels are significant challenges in the training of machine learning models, particularly in complex datasets. This paper introduces a novel checkpointing method designed to miti...
详细信息
In recent years, there has been an energy transition in which fossil fuel-fired power plants are being replaced by renewable energy sources such as photovoltaics. While the influence of factors such as location and me...
详细信息
Visual event sensors only output data when changes in the scene happen at very high frequency. This allows for smartly compressing the scene and thus, enabling real-time operation. Despite these advantages, works in t...
详细信息
Accurate detection of respiratory pauses is crucial in patients undergoing cataract surgery under sedation, as undetected pauses can lead to serious complications. Conventional monitoring techniques, such as pulse oxi...
详细信息
This study provides an innovative architectural model for e-Health systems that aims to improve cyber resilience while maintaining high availability under fluctuating traffic loads. We examined typical cybersecurity i...
详细信息
This paper proposes a design and implementation of a highly efficient feature selection based on Minkowski's mathematical similarity for machine learning. Moreover, the development of the Minkowski feature selecti...
详细信息
Domain incremental learning (DIL) poses a significant challenge in real-world scenarios, as models need to be sequentially trained on diverse domains over time, all the while avoiding catastrophic forgetting. Mitigati...
详细信息
Domain incremental learning (DIL) poses a significant challenge in real-world scenarios, as models need to be sequentially trained on diverse domains over time, all the while avoiding catastrophic forgetting. Mitigating representation drift, which refers to the phenomenon of learned representations undergoing changes as the model adapts to new tasks, can help alleviate catastrophic forgetting. In this study, we propose a novel DIL method named DARE, featuring a three-stage training process: Divergence, Adaptation, and REfinement. This process gradually adapts the representations associated with new tasks into the feature space spanned by samples from previous tasks, simultaneously integrating task-specific decision boundaries. Additionally, we introduce a novel strategy for buffer sampling and demonstrate the effectiveness of our proposed method, combined with this sampling strategy, in reducing representation drift within the feature encoder. This contribution effectively alleviates catastrophic forgetting across multiple DIL benchmarks. Furthermore, our approach prevents sudden representation drift at task boundaries, resulting in a well-calibrated DIL model that maintains the performance on previous tasks. Copyright 2024 by the author(s)
While humans excel at continual learning (CL), deep neural networks (DNNs) exhibit catastrophic forgetting. A salient feature of the brain that allows effective CL is that it utilizes multiple modalities for learning ...
详细信息
Robotic arms play an important role in the automation industry. Robotic arms plan processing paths based on the shape of the workpiece. However, the processing path often deviates due to inaccurate placement of the wo...
详细信息
暂无评论