Abstract
In recent years, self-paced learning (SPL) has attracted much attention due to its improvement to nonconvex optimization based machine learning algorithms. As a methodology introduced from human learning, SPL dynamically evaluates the learning difficulty of each sample and provides the weighted learning model against the negative effects from hard-learning samples. In this study, we proposed a cognitive driven SPL method, i.e., retrospective robust self-paced learning (R2SPL), which is inspired by the following two issues in human learning process: the misclassified samples are more impressive in upcoming learning, and the model of the follow-up learning process based on large number of samples can be used to reduce the risk of poor generalization in initial learning phase. We simultaneously estimated the degrees of learning-difficulty and misclassified in each step of SPL and proposed a framework to construct multilevel SPL for improving the robustness of the initial learning phase of SPL. The proposed method can be viewed as a multilayer model and the output of the previous layer can guide constructing robust initialization model of the next layer. The experimental results show that the R2SPL outperforms the conventional self-paced learning models in classification task.
Highlights
We proposed a cognitive driven SPL method, i.e., retrospective robust self-paced learning (R2SPL), which is inspired by the following two issues in human learning process: the misclassified samples are more impressive in upcoming learning, and the model of the follow-up learning process based on large number of samples can be used to reduce the risk of poor generalization in initial learning phase
By assigning the samples in a meaningful learning order based on prior knowledge, curriculum learning (CL) [1] provides an easy-to-hard learning process, which makes the model more fits human cognition
We verify the effectiveness of introducing tough samples and retrospective self-paced learning to the model in each iteration on ten UCI datasets
Summary
By assigning the samples in a meaningful learning order based on prior knowledge, curriculum learning (CL) [1] provides an easy-to-hard learning process, which makes the model more fits human cognition. In the literature [3], Jiang et al proposed the self-paced curriculum learning, which obtains the dynamic sample sequence in the process of model learning, and makes use of prior knowledge to avoid overfitting. Zhao et al [4] applied the nonconvex problem of matrix decomposition, which suppresses effectiveness of the noise and outlier in the data on the model. They pointed out that the strategy of adaptively selecting easylearning sample sequences is similar to the process of human cognition. Self-paced learning has been introduced to many learning models and shown good performance in many real-world applications
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
