[Retracted] Review on the Application of Metalearning in Artificial Intelligence

Abstract

In recent years, artificial intelligence supported by big data has gradually become more dependent on deep reinforcement learning. However, the application of deep reinforcement learning in artificial intelligence is limited by prior knowledge and model selection, which further affects the efficiency and accuracy of prediction, and also fails to realize the learning ability of autonomous learning and prediction. Metalearning came into being because of this. Through learning the information metaknowledge, the ability to autonomously judge and select the appropriate model can be formed, and the parameters can be adjusted independently to achieve further optimization. It is a novel method to solve big data problems in the current neural network model, and it adapts to the development trend of artificial intelligence. This article first briefly introduces the research process and basic theory of metalearning and discusses the differences between metalearning and machine learning and the research direction of metalearning in big data. Then, four typical applications of metalearning in the field of artificial intelligence are summarized: few-shot learning, robot learning, unsupervised learning, and intelligent medicine. Then, the challenges and solutions of metalearning are analyzed. Finally, a systematic summary of the full text is made, and the future development prospect of this field is assessed.

Information Extraction from the Text Data on Traditional Chinese Medicine: A Review on Tasks, Challenges, and Methods from 2010 to 2021

“…Few-shot learning brings AI technology closer to human intelligence. Currently, meta-learning and few-shot learning have been applied in classification and target detection [75]. In the field of TCM text processing, they also have positive prospects and opportunities.…”

Hybrid Fine-Tuning Strategy for Few-Shot Classification

“…Currently, many works have been proposed to address FSC [ 11 – 19 ], which can be mainly divided into three categories: initialization-based methods, metric-based methods, and hallucination-based methods. Initialization-based methods use the target dataset to fine-tune the pretrained model with a small number of gradient backpropagation steps [ 20 , 21 ].…”

“…Few-Shot Classification. Currently, many works have been proposed to address FSC [11][12][13][14][15][16][17][18][19], which can be mainly divided into three categories: initialization-based methods, metric-based methods, and hallucination-based methods.…”

Early warning model of recurrence site for breast cancer rehabilitation patients based on adaptive mesh optimization XGBoost

“…With the continuous improvement of living standards, the environment and lifestyle of humans have also changed and improved accordingly, but the ensuing cancer issue still remains one of the most serious problems threatening human health. The "Global Cancer Incidence and Mortality in 2018" (GLOBOCAN 2018) [1,2] estimated that there were approximately 18.1 million new cancer cases and 9.6 million cancer deaths worldwide in 2018, with a high incidence of cancer in both developed and developing countries. According to data released by the World Health Organization's International Center for Research on Cancer, cancer accounts for ~13% of all deaths every year.…”