Results 31 to 40 of about 3,000 (250)
Catastrophic Forgetting: Still a Problem for DNNs [PDF]
, 2018 We investigate the performance of DNNs when trained on class-incremental visual problems consisting of initial training, followed by retraining with added visual classes. Catastrophic forgetting (CF) behavior is measured using a new evaluation procedure that aims at an application-oriented view of incremental learning.
Benedikt Pfülb +3 more
openaire +2 more sources
On Robustness of Generative Representations Against Catastrophic Forgetting [PDF]
, 2021 Catastrophic forgetting of previously learned knowledge while learning new tasks is a widely observed limitation of contemporary neural networks. Although many continual learning methods are proposed to mitigate this drawback, the main question remains unanswered: what is the root cause of catastrophic forgetting? In this work, we aim at answering this
Wojciech Masarczyk +2 more
openaire +3 more sources
CL3: Generalization of Contrastive Loss for Lifelong Learning
Journal of Imaging, 2023 Lifelong learning portrays learning gradually in nonstationary environments and emulates the process of human learning, which is efficient, robust, and able to learn new concepts incrementally from sequential experience.
Kaushik Roy +3 more
doaj +1 more source
Continual Learning With Speculative Backpropagation and Activation History
IEEE Access, 2022 Continual learning is gaining traction these days with the explosive emergence of deep learning applications. Continual learning suffers from a severe problem called catastrophic forgetting.
Sangwoo Park, Taeweon Suh
doaj +1 more source
Multi-Scopic Cognitive Memory System for Continuous Gesture Learning
Biomimetics, 2023 With the advancement of artificial intelligence technologies in recent years, research on intelligent robots has progressed. Robots are required to understand human intentions and communicate more smoothly with humans.
Wenbang Dou +2 more
doaj +1 more source
Habituation based synaptic plasticity and organismic learning in a quantum perovskite
Nature Communications, 2017 Habituation is a learning mechanism that enables control over forgetting and learning. Zuo, Panda et al., demonstrate adaptive synaptic plasticity in SmNiO3 perovskites to address catastrophic forgetting in a dynamic learning environment via hydrogen ...
Fan Zuo +16 more
doaj +1 more source
Forget Me Not: Reducing Catastrophic Forgetting for Domain Adaptation in Reading Comprehension [PDF]
2020 International Joint Conference on Neural Networks (IJCNN), 2020 The creation of large-scale open domain reading comprehension data sets in recent years has enabled the development of end-to-end neural comprehension models with promising results. To use these models for domains with limited training data, one of the most effective approach is to first pretrain them on large out-of-domain source data and then fine ...
Ying Xu +3 more
openaire +2 more sources
Overcoming Catastrophic Forgetting With Unlabeled Data in the Wild [PDF]
2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019 ICCV 2019; v3 updated Figure ...
Kibok Lee 0003 +3 more
openaire +2 more sources
Investigating Catastrophic Forgetting of Deep Learning Models Within Office 31 Dataset
IEEE AccessDeep learning models have shown impressive performance in various tasks. However, they are prone to a phenomenon called catastrophic forgetting. This means they do not remember what they have learned when training on new tasks. In this research paper, we
Hidayaturrahman +3 more
doaj +1 more source
Incremental Learning With Adaptive Model Search and a Nominal Loss Model
IEEE Access, 2022 This paper addresses an incremental learning problem, in which tasks are learned sequentially without access to the previously trained dataset. Catastrophic forgetting is a significant bottleneck to incremental learning as the network performs poorly on ...
Chanho Ahn, Eunwoo Kim, Songhwai Oh
doaj +1 more source