Results 51 to 60 of about 339,627 (329)

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

Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning [PDF]

International Conference on Learning Representations, 2023
Federated Learning (FL) has gained significant attraction due to its ability to enable privacy-preserving training over decentralized data. Current literature in FL mostly focuses on single-task learning.
Yavuz Faruk Bakman, D. Yaldiz, Yahya H. Ezzeldin, A. Avestimehr   +3 more
semanticscholar   +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, Weihong Chin, Naoyuki Kubota   +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, Priyadarshini Panda, Michele Kotiuga, Jiarui Li, Mingu Kang, Claudio Mazzoli, Hua Zhou, Andi Barbour, Stuart Wilkins, Badri Narayanan, Mathew Cherukara, Zhen Zhang, Subramanian K. R. S. Sankaranarayanan, Riccardo Comin, Karin M. Rabe, Kaushik Roy, Shriram Ramanathan   +16 more
doaj   +1 more source

Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition

, 2020
We introduce a probabilistic approach to unify open set recognition with the prevention of catastrophic forgetting in deep continual learning, based on variational Bayesian inference.
Hong, Yong Won, Majumder, Sagnik, Mundt, Martin, Pliushch, Iuliia, Ramesh, Visvanathan   +4 more
core   +1 more source

Behavioral Experiments for Understanding Catastrophic Forgetting

, 2021
In this paper we explore whether the fundamental tool of experimental psychology, the behavioral experiment, has the power to generate insight not only into humans and animals, but artificial systems too. We apply the techniques of experimental psychology to investigating catastrophic forgetting in neural networks.
Bell, Samuel J., Lawrence, Neil D.
openaire   +2 more sources

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

Continual Learning Objective for Analyzing Complex Knowledge Representations

Sensors, 2022
Human beings tend to incrementally learn from the rapidly changing environment without comprising or forgetting the already learned representations. Although deep learning also has the potential to mimic such human behaviors to some extent, it suffers ...
Asad Mansoor Khan, Taimur Hassan, Muhammad Usman Akram, Norah Saleh Alghamdi, Naoufel Werghi   +4 more
doaj   +1 more source

Overcoming Catastrophic Forgetting by XAI

, 2022
Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life. Taking the advantages of interpretable machine learning (interpretable ML), this work proposes a novel tool called Catastrophic Forgetting Dissector (or CFD) to explain ...
openaire   +2 more sources

Challenging Common Assumptions about Catastrophic Forgetting

, 2022
Building learning agents that can progressively learn and accumulate knowledge is the core goal of the continual learning (CL) research field. Unfortunately, training a model on new data usually compromises the performance on past data. In the CL literature, this effect is referred to as catastrophic forgetting (CF).
Lesort, Timothée, Ostapenko, Oleksiy, Misra, Diganta, Arefin, Md Rifat, Rodríguez, Pau, Charlin, Laurent, Rish, Irina   +6 more
openaire   +2 more sources