Search
Search Results
-
Informative representations for forgetting-robust knowledge tracing
Tracing a student’s knowledge state is critical for teaching and learning. Knowledge tracing aims to accurately predict student performance by...
-
Compositional Prompting for Anti-Forgetting in Domain Incremental Learning
Domain Incremental Learning (DIL) focuses on handling complex domain shifts of a continuous data stream for visual tasks such as image classification...
-
Adaptive trajectory prediction without catastrophic forgetting
Pedestrian trajectory prediction is a necessary component of autonomous driving technology. However, current methods face two troubles when utilized...
-
Lifelong iris presentation attack detection without forgetting
Despite the promising results achieved by deep iris presentation attack detection (PAD) in dataset-specific scenarios, the advanced approach remains...
-
Knowledge forgetting in propositional μ-calculus
The μ -calculus is one of the most important logics describing specifications of transition systems. It has been extensively explored for formal...
-
From Forgetting Signature Elements to Forgetting Formulas in Epistemic States
In this paper, we bring together marginalization and forgetting of signature elements in the framework of epistemic states. Marginalization of...
-
Fault estimator design based on an iterative-learning scheme according to the forgetting factor for nonlinear systems
In this study, an iterative-learning-based fault estimator with the forgetting factor is proposed in response to the requirement of fault estimation...
-
Transfer Without Forgetting
This work investigates the entanglement between Continual Learning (CL) and Transfer Learning (TL). In particular, we shed light on the widespread...
-
Propositional Variable Forgetting and Marginalization: Semantically, Two Sides of the Same Coin
This paper investigates variable forgetting and marginalization in propositional logic. We show that for finite signatures and infinite signatures,...
-
Causes of Catastrophic Forgetting in Class-Incremental Semantic Segmentation
Class-incremental learning for semantic segmentation (CiSS) is presently a highly researched field which aims at updating a semantic segmentation...
-
Online Hybrid Kernel Learning Machine with Dynamic Forgetting Mechanism
This paper, for the purpose of meeting challenges of fewer resources of storage and calculation in the detection of ICS intrusion as well as...
-
Using Flexible Memories to Reduce Catastrophic Forgetting
In continual learning, a primary factor of catastrophic forgetting is task-recency bias, which arises when a model is trained on an imbalanced set of...
-
Continual Vocabularies to Tackle the Catastrophic Forgetting Problem in Machine Translation
Neural Machine Translation (NMT) models are rarely decoupled from their vocabularies, as both are often trained together in an end-to-end fashion....
-
Overcoming Catastrophic Forgetting via Direction-Constrained Optimization
This paper studies a new design of the optimization algorithm for training deep learning models with a fixed architecture of the classification...
-
Learning-Without-Forgetting via Memory Index in Incremental Object Detection
Object detection has made significant progress in recent years. However, when the training data is continuous and dynamic, notorious catastrophic...
-
Does Catastrophic Forgetting Negatively Affect Financial Predictions?
Nowadays, financial markets produce a large amount of data, in the form of historical time series, which quantitative researchers have recently...
-
Building user interest model for TV recommendation with label-based memory forgetting-enhancement model
TV recommendation can help users find interesting TV programs, improve user experience, and solve the problem of information overload. Current TV...
-
Learning with Recoverable Forgetting
Life-long learning aims at learning a sequence of tasks without forgetting the previously acquired knowledge. However, the involved training data may...
-
An improved crow search algorithm based on oppositional forgetting learning
Crow search algorithm (CSA) is a novel meta-heuristic optimization algorithm based on the intelligent behavior of the crow population. Although the...
-
Novel Class Discovery Without Forgetting
Humans possess an innate ability to identify and differentiate instances that they are not familiar with, by leveraging and adapting the knowledge...