Results 101 to 110 of about 151,060 (281)

Continual Test-Time Adaptation for Robust Remote Photoplethysmography Estimation

IEEE Access
Remote photoplethysmography (rPPG) estimation has made considerable progress by leveraging deep learning, yet its performance remains highly susceptible to the domain shifts caused by lighting, skin tone and movement, particularly during inference ...
Hyunwoo Lee, Haechang Lee, Byung Hyun Lee, Se Young Chun   +3 more
doaj   +1 more source

Predicting the Susceptibility of Examples to Catastrophic Forgetting

Catastrophic forgetting - the tendency of neural networks to forget previously learned data when learning new information - remains a central challenge in continual learning. In this work, we adopt a behavioral approach, observing a connection between learning speed and forgetting: examples learned more quickly are less prone to forgetting. Focusing on
Guy Hacohen, Tinne Tuytelaars
openaire   +3 more sources

Preventing catastrophic forgetting in continual learning

, 2022
Continual learning in neural networks has been receiving increased interest due to how prevalent machine learning is in an increasing number of industries.
Ong, Yi Shen
core  

Living with the Unknown: Intolerance of Uncertainty in Parkinson's Disease

Movement Disorders Clinical Practice, EarlyView.
Abstract Background Parkinson's disease (PD) is marked by pervasive uncertainty due to fluctuating motor and non‐motor symptoms, variable treatment response, and an unpredictable clinical course. Intolerance of uncertainty (IU), a tendency to perceive ambiguity as threatening and respond with worry, avoidance, or decisional paralysis, may be ...
Bradley McDaniels, Gregory M. Pontone, Kuhan Pushparatnam, Indu Subramanian   +3 more
wiley   +1 more source

Dynamic Performance Enhancement of a High‐Agility Hypersonic Mechanical System via a Learning‐Augmented Robust Control Architecture

International Journal of Mechanical System Dynamics, EarlyView.
ABSTRACT The design of control systems for high‐agility mechanical systems operating in extreme environments is a significant challenge in nonlinear dynamics. This paper addresses the complex dynamic control problem of a hypersonic interceptor, modeled as a multi‐input multi‐output (MIMO) mechanical system characterized by strong aerodynamic cross ...
Mohammad Mahdi Soori, Seyed Hossein Sadati   +1 more
wiley   +1 more source

EXACFS - A CIL Method to Mitigate Catastrophic Forgetting

Proceedings of the Fifteenth Indian Conference on Computer Vision Graphics and Image Processing
Deep neural networks (DNNS) excel at learning from static datasets but struggle with continual learning, where data arrives sequentially. Catastrophic forgetting, the phenomenon of forgetting previously learned knowledge, is a primary challenge. This paper introduces EXponentially Averaged Class-wise Feature Significance (EXACFS) to mitigate this issue
S. Balasubramanian 0001, M. Sai Subramaniam, Sai Sriram Talasu, Manepalli Pranav Phanindra Sai, Yedu Krishna P, Darshan Gera, Ravi Mukkamala   +6 more
openaire   +4 more sources

Deep Reinforcement Learning‐Based Control for Real‐Time Hybrid Simulation of Civil Structures

International Journal of Robust and Nonlinear Control, EarlyView.
ABSTRACT Real‐time Hybrid Simulation (RTHS) is a cyber‐physical technique that studies the dynamic behavior of a system by combining physical and numerical components that are coupled through a boundary condition enforcer. In structural engineering, the numerical components are subjected to environmental loads that become dynamic displacements of the ...
Andrés Felipe Niño, Alejandro Palacio‐Betancur, Piedad Miranda‐Chiquito, Juan David Amaya, Christian E. Silva, Mariantonieta Gutierrez Soto, Luis Felipe Giraldo   +6 more
wiley   +1 more source

Unsupervised Learning to Overcome Catastrophic Forgetting in Neural Networks

IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, 2019
Continual learning is the ability to acquire a new task or knowledge without losing any previously collected information. Achieving continual learning in artificial intelligence (AI) is currently prevented by catastrophic forgetting, where training of a ...
Irene Munoz-Martin, Stefano Bianchi, Giacomo Pedretti, Octavian Melnic, Stefano Ambrogio, Daniele Ielmini   +5 more
doaj   +1 more source

National Policy Coherence Counts for Reducing Inequality in Global Climate and Development Agendas

Sustainable Development, EarlyView.
ABSTRACT International institutions promote policy coherence as crucial to the effective and fair implementation of global sustainability agendas, though the evidence for its benefits is slim. We present here the first systematic cross‐country dataset on the consequences of national government efforts to promote policy coherence for vulnerable groups ...
Katherine Browne, Adis Dzebo, Zoha Shawoo, Mario Cardenas, Pierrick Chalaye, Alexia Faus Onbargi, Cassilde Muhoza, Patricia Nicdao, Nokwethaba Makhanya, Navam Niles, Priyatma Singh   +10 more
wiley   +1 more source

Benchmarking Catastrophic Forgetting in Neural Networks [PDF]

, 2006
Catastrophic Forgetting is a behavior seen in artificial neural networks (ANNs) when new information overwrites old in such a way that the old information is no longer usable.
Moe-Helgesen, Ole-Marius
core   +1 more source