Results 51 to 60 of about 3,000 (250)

Overcoming Catastrophic Forgetting Using Sparse Coding and Meta Learning

IEEE Access, 2021
Continuous learning occurs naturally in human beings. However, Deep Learning methods suffer from a problem known as Catastrophic Forgetting (CF) that consists of a model drastically decreasing its performance on previously learned tasks when it is ...
Julio Hurtado, Hans Lobel, Alvaro Soto
doaj   +1 more source

Overcoming Catastrophic Forgetting in Graph Neural Networks

Proceedings of the AAAI Conference on Artificial Intelligence, 2021
Catastrophic forgetting refers to the tendency that a neural network ``forgets'' the previous learned knowledge upon learning new tasks. Prior methods have been focused on overcoming this problem on convolutional neural networks (CNNs), where the input samples like images lie in a grid domain, but have largely overlooked graph neural networks (GNNs ...
Huihui Liu, Yiding Yang, Xinchao Wang
openaire   +2 more sources

Continual Learning for Multimodal Data Fusion of a Soft Gripper

Advanced Robotics Research, EarlyView.
Models trained on a single data modality often struggle to generalize when exposed to a different modality. This work introduces a continual learning algorithm capable of incrementally learning different data modalities by leveraging both class‐incremental and domain‐incremental learning scenarios in an artificial environment where labeled data is ...
Nilay Kushawaha, Egidio Falotico
wiley   +1 more source

Self-Organizing Multiple Readouts for Reservoir Computing

IEEE Access, 2023
With advancements in deep learning (DL), artificial intelligence (AI) technology has become an indispensable tool. However, the application of DL incurs significant computational costs, making it less viable for edge AI scenarios.
Yuichiro Tanaka, Hakaru Tamukoh
doaj   +1 more source

Addressing catastrophic forgetting for medical domain expansion

CoRR, 2021
Model brittleness is a key concern when deploying deep learning models in real-world medical settings. A model that has high performance at one institution may suffer a significant decline in performance when tested at other institutions. While pooling datasets from multiple institutions and retraining may provide a straightforward solution, it is ...
Sharut Gupta, Praveer Singh, Ken Chang, Liangqiong Qu, Mehak Aggarwal, Nishanth Thumbavanam Arun, Ashwin Vaswani, Shruti Raghavan, Vibha Agarwal, Mishka Gidwani, Katharina Hoebel, Jay B. Patel, Charles Lu 0001, Christopher P. Bridge, Daniel L. Rubin, Jayashree Kalpathy-Cramer   +15 more
openaire   +2 more sources

Intelligent Maintenance Review for Robots: Multimodal Information, Deep Diagnosis and Embodied Artificial Intelligence

Advanced Robotics Research, EarlyView.
This review maps the methods to monitor robots’ health by fusing vibration, sound, control signals, vision, force, and oil information with artificial intelligence. It identifies deep learning, transfer learning, digital twins, and physics‐informed models as key methodological pathways enabling earlier diagnosis, safer human–robot collaboration, and ...
Yuting Qiao, Hongbo Wang, Naipeng Li, Shuo Wang, Yaguo Lei, Tonghai Wu, Junyi Cao   +6 more
wiley   +1 more source

Cosine Prompt-Based Class Incremental Semantic Segmentation for Point Clouds

Algorithms
Although current 3D semantic segmentation methods have achieved significant success, they suffer from catastrophic forgetting when confronted with dynamic, open environments.
Lei Guo, Hongye Li, Min Pang, Kaowei Liu, Xie Han, Fengguang Xiong   +5 more
doaj   +1 more source

Learning‐Based Soft Robotic Grasping: Recent Progress and Remaining Challenges

Advanced Robotics Research, EarlyView.
This review analyzes learning‐based soft robotic grasping from a pipeline‐oriented perspective, encompassing soft gripper design, multimodal sensing, and learning‐based planning and control. It surveys key neural network architectures and benchmark datasets and identifies critical challenges such as sim‐to‐real transfer, generalization, and continual ...
Arnab Majumder, Jelizaveta Konstantinova, Graham Deacon, Kaspar Althoefer   +3 more
wiley   +1 more source

Solutions to the Catastrophic Forgetting Problem [PDF]

, 2022
In this paper we review three kinds of proposed solutions to the catastrophic forgetting problem in neural networks. The solutions are based on reducing hidden unit overlap, rehearsal, and pseudorehearsal mechanisms. We compare the methods and identify some underlying similarities.
openaire   +1 more source

Physics‐Embedded Neural Network: A Novel Approach to Design Polymeric Materials

Advanced Science, EarlyView.
Traditional black‐box models for polymer mechanics rely solely on data and lack physical interpretability. This work presents a physics‐embedded neural network (PENN) that integrates constitutive equations into machine learning. The approach ensures reliable stress predictions, provides interpretable parameters, and enables performance‐driven, inverse ...
Siqi Zhan, Hengheng Zhao, Haotian Wang, Zhanjie Liu, Qian Li, Weifeng Zhang, Qingsong Zhao, Liqun Zhang, Jun Liu   +8 more
wiley   +1 more source