Overview
The tendency of neural networks to completely lose previously learned knowledge when trained on new tasks, a fundamental challenge in continual and multi-task learning.
Cross-References(1)
More in Machine Learning
Machine Learning
MLOps & ProductionA subset of AI that enables systems to automatically learn and improve from experience without being explicitly programmed.
Clustering
Unsupervised LearningUnsupervised learning technique that groups similar data points together based on inherent patterns without predefined labels.
Principal Component Analysis
Unsupervised LearningA dimensionality reduction technique that transforms data into orthogonal components ordered by the amount of variance they explain.
Adam Optimiser
Training TechniquesAn adaptive learning rate optimisation algorithm combining momentum and RMSProp for efficient deep learning training.
Feature Store
MLOps & ProductionA centralised repository for storing, managing, and serving machine learning features, ensuring consistency between training and inference environments across an organisation.
Gradient Descent
Training TechniquesAn optimisation algorithm that iteratively adjusts parameters in the direction of steepest descent of the loss function.
Learning Rate
Training TechniquesA hyperparameter that controls how much model parameters are adjusted with respect to the loss gradient during training.
DBSCAN
Unsupervised LearningDensity-Based Spatial Clustering of Applications with Noise — a clustering algorithm that finds arbitrarily shaped clusters based on density.