National Research Foundation (NRF) Singapore under International Research Centre in Singapore Funding Initiativ
Meta-learning has gained wide popularity as a training framework that is more data-efficient than tr...
Despite huge progress in artificial intelligence, the ability to quickly learn from few examples is ...
This thesis focuses on integrating learning paradigms that ‘share to learn,’ i.e., Multitask Learnin...
Meta-Learning, or so-called Learning to learn, has become another important research branch in Machi...
Humans show a remarkable capability to accurately solve a wide range of problems efficiently -- util...
Over the past decade, the field of machine learning has experienced remarkable advancements. While i...
Deep neural networks can achieve great successes when presented with large data sets and sufficient ...
In order to make predictions with high accuracy, conventional deep learning systems require large tr...
The ability to learn quickly from a few samples is a vital element of intelligence. Humans can reuse...
Deep learning has achieved classification performance matching or exceeding the human one, as long a...
Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large ...
In this paper, we consider the framework of multi-task representation (MTR) learning where the goal ...
Integrating knowledge across different domains is an essential feature of human learning. Learning p...
Meta-learning has been shown to be an effective strategy for few-shot learning. The key idea is to l...
Few-shot learning aims to scale visual recognition to open-ended growth of new classes with limited ...
Meta-learning has gained wide popularity as a training framework that is more data-efficient than tr...
Despite huge progress in artificial intelligence, the ability to quickly learn from few examples is ...
This thesis focuses on integrating learning paradigms that ‘share to learn,’ i.e., Multitask Learnin...
Meta-Learning, or so-called Learning to learn, has become another important research branch in Machi...
Humans show a remarkable capability to accurately solve a wide range of problems efficiently -- util...
Over the past decade, the field of machine learning has experienced remarkable advancements. While i...
Deep neural networks can achieve great successes when presented with large data sets and sufficient ...
In order to make predictions with high accuracy, conventional deep learning systems require large tr...
The ability to learn quickly from a few samples is a vital element of intelligence. Humans can reuse...
Deep learning has achieved classification performance matching or exceeding the human one, as long a...
Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large ...
In this paper, we consider the framework of multi-task representation (MTR) learning where the goal ...
Integrating knowledge across different domains is an essential feature of human learning. Learning p...
Meta-learning has been shown to be an effective strategy for few-shot learning. The key idea is to l...
Few-shot learning aims to scale visual recognition to open-ended growth of new classes with limited ...
Meta-learning has gained wide popularity as a training framework that is more data-efficient than tr...
Despite huge progress in artificial intelligence, the ability to quickly learn from few examples is ...
This thesis focuses on integrating learning paradigms that ‘share to learn,’ i.e., Multitask Learnin...
DOI
Add to ORKG