Results 41 to 50 of about 10,284,296 (292)
Feature Transformation Network for Few-Shot Learning
IEEE Access, 2021 Few-shot learning researches to learn a novel concept from a handful of labeled samples. Due to the small amount of training data, deep network has the risk of over-fitting. Although many previous approaches based on metric criterion can make significant
Xiaoyan Wang, Hongmei Wang, Daming Zhou
doaj +1 more source
Applying a Probabilistic Network Method to Solve Business-Related Few-Shot Classification Problems
Complexity, 2021 It can be challenging to learn algorithms due to the research of business-related few-shot classification problems. Therefore, in this paper, we evaluate the classification of few-shot learning in the commercial field.
Lang Wu, Menggang Li
doaj +1 more source
Few-Shot Learning for Low-Data Drug Discovery
, 2022 The discovery of new hits through ligand-based virtual screening in drug discovery is essentially a low-data problem, as data acquisition is both difficult and expensive.
Jean-Paul Ebejer (1747735) +1 more
core +1 more source
Empowering Few-Shot Learning through Domain Adaptation
, 2023 Few-shot learning is a fascinating subfield of machine learning that addresses the challenge of training models to recognize and generalize from a limited amount of data.
fidelicy flex, Ramond Jude
core +1 more source
Subgraph-aware Few-Shot Inductive Link Prediction via Meta-Learning
, 2022 Link prediction for knowledge graphs aims to predict missing connections between entities. Prevailing methods are limited to a transductive setting and hard to process unseen entities.
Mai, S +9 more
core +1 more source
Improving Augmentation Efficiency for Few-Shot Learning
IEEE Access, 2022 While human intelligence can easily recognize some characteristics of classes with one or few examples, learning from few examples is a challenging task in machine learning.
Wonhee Cho, Eunwoo Kim
doaj +1 more source
Active Few-Shot Learning with FASL
, 2022 Recent advances in natural language processing (NLP) have led to strong text classification models for many tasks. However, still often thousands of examples are needed to train models with good quality. This makes it challenging to quickly develop and deploy new models for real world problems and business needs.
Thomas Müller 0009 +3 more
openaire +4 more sources
Few-shot Learning: Methods and Applications [PDF]
ITM Web of ConferencesThe Few-shot learning (FSL) approach distills meaningful features from a constrained sample set, allowing models to swiftly adjust to novel tasks and decreasing the dependency on extensive datasets. This approach leverages methods involving meta-learning,
Li Jiaxiang, Li Mingyang
doaj +1 more source
Heterogeneous Ensemble-Based Spike-Driven Few-Shot Online Learning
Frontiers in Neuroscience, 2022 Spiking neural networks (SNNs) are regarded as a promising candidate to deal with the major challenges of current machine learning techniques, including the high energy consumption induced by deep neural networks.
Shuangming Yang +2 more
doaj +1 more source
Few-Shot Classification with Contrastive Learning
, 2022 To appear in ECCV ...
Zhanyuan Yang +2 more
openaire +4 more sources