Saman Halgamuge
5 papers · 2019–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (4) π Academic Marathon (5) π Cross-Pollinator (10) πΊοΈ Taxonomy Completionist (14)
π§
Keyword Pioneer
β
The Questioner
Conferences
AAAI (2)
CVPR (1)
ICCV (1)
ICLR (1)
Top co-authors
Keywords
continual learning
(1)
catastrophic forgetting
(1)
neural network training
(1)
feature representation
(1)
vector quantization
(1)
interpretable neural network
(1)
cross-domain few-shot learning
(1)
symbolic regression
(1)
parameter-efficient adaptation
(1)
equation discovery
(1)
network expansion
(1)
sparsity regularization
(1)
regularization effect
(1)
neighbor embedding
(1)
overfitting prevention
(1)
multivariate polynomial
(1)
nearest centroid classifier
(1)
prototype augmentation
(1)
network growth
(1)
discriminative loss
(1)
Papers
When to Grow? A Fitting Risk-Aware Policy for Layer Growing in Deep Neural Networks
AAAI 2024
GINN-LP: A Growing Interpretable Neural Network for Discovering Multivariate Laurent Polynomial Equations
AAAI 2024
Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning
CVPR 2024
NAPA-VQ: Neighborhood-Aware Prototype Augmentation with Vector Quantization for Continual Learning
ICCV 2023
Improving MMD-GAN Training with Repulsive Loss Function
ICLR 2019