Fast Task Adaptation Based on the Combination of Model-Based and Gradient-Based Meta Learning

Xu, Zongben; Chen, Xiliang; Cao, Lei

doi:10.1109/tcyb.2020.3028378

Cited by 13 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many methods have recently been proposed to implement few-shot learning tasks, which can be categorized into three types [8]: memory-based, optimization-based, and metricbased. Memory-based methods extend a memory space to store key training examples or model-related information [9], which are often achieved by applying attention models [10], [11]. Optimization-based methods learn to control the process of optimization for a given task by learning the initial parameters (e.g., [12], [13]) or the underlying optimizer (e.g., [14]- [16]).…”

Section: Introductionmentioning

confidence: 99%

Decoder Choice Network for Metalearning

Liu

Chao

Yang

et al. 2023

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Metalearning has been widely applied for implementing few-shot learning and fast model adaptation. Particularly, existing metalearning methods have been exploited to learn the control mechanism for gradient descent processes, in an effort to facilitate gradient-based learning in gaining high speed and generalization ability. This paper presents a novel method that controls the gradient descent process of the model parameters in a neural network, by limiting the model parameters within a low-dimensional latent space. The main challenge for implementing this idea is that a decoder with many parameters may be required. To tackle this problem, the paper provides an alternative design of the decoder with a structure that shares certain weights, thereby reducing the number of required parameters. In addition, this work combines ensemble learning with the proposed approach to improve the overall learning performance. Systematic experimental studies demonstrate that the proposed approach offers results superior to the state-of-theart in performing the Omniglot classification and miniImageNet classification tasks.

show abstract

Section: Introductionmentioning

confidence: 99%

Decoder Choice Network for Metalearning

Liu

Chao

Yang

et al. 2023

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

“…adaptation to unforeseen physical changes). Such rapid adaptation is possible as learning never occurs from scratch, but previous experience is used as a prior to learn faster [14].…”

Section: Introductionmentioning

confidence: 99%

Deep Meta-Learning Energy-Aware Path Planner for Unmanned Ground Vehicles in Unknown Terrains

et al. 2022

View full text Add to dashboard Cite

show abstract

“…It uses meta-learning algorithms to learn how best to combine predictions from two or more basic machine learning algorithms such as KNN, SVM, and DT. Meta-learning is the ability to "learn to learn" like humans (14). In meta-learning, each model is trained with a different set of training tasks and such models are combined to form a body of knowledge that is applied to a new unknown task and the results are analyzed (15).…”

Section: Introductionmentioning

confidence: 99%

A hybrid breast cancer classification algorithm based on meta-learning and artificial neural networks

Han

Yin

2022

Front. Oncol.

View full text Add to dashboard Cite

The incidence of breast cancer in women has surpassed that of lung cancer as the world’s leading new cancer case. Regular screening and measures become an effective way to prevent breast cancer and also provide a good foundation for later treatment. Women should receive regular checkups in the hospital after reaching a certain age. The use of computer-aided technology can improve the accuracy and efficiency of physicians’ decision-making. Data pre-processing is required before data analysis, and 16 features are selected using a correlation-based feature selection method. In this paper, meta-learning and Artificial Neural Networks (ANN) are combined to create a hybrid algorithm. The proposed hybrid algorithm for predicting breast cancer was attempted to achieve 98.74% accuracy and 98.02% F1-score by creating a combination of various meta-learning models whose output was used as input features for creating ANN models. Therefore, the hybrid algorithm proposed in this paper can obtain better prediction results than a single model.

show abstract

Fast Task Adaptation Based on the Combination of Model-Based and Gradient-Based Meta Learning

Cited by 13 publications

References 14 publications

Decoder Choice Network for Metalearning

Decoder Choice Network for Metalearning

Deep Meta-Learning Energy-Aware Path Planner for Unmanned Ground Vehicles in Unknown Terrains

A hybrid breast cancer classification algorithm based on meta-learning and artificial neural networks

Contact Info

Product

Resources

About