Gated recurrent units and temporal convolutional network for multilabel classification

Abstract

Multilabel learning tackles the problem of associating a sample with multiple class labels. This work proposes a new ensemble method for managing multilabel classification: the core of the proposed approach combines a set of gated recurrent units and temporal convolutional neural networks trained with variants of the Adam optimization approach. Multiple Adam variants, including novel one proposed here, are compared and tested; these variants are based on the difference between present and past gradients, with step size adjusted for each parameter. The proposed neural network approach is also combined with Incorporating Multiple Clustering Centers (IMCC), which further boosts classification performance. Multiple experiments on nine data sets representing a wide variety of multilabel tasks demonstrate the robustness of our best ensemble, which is shown to outperform the state-of-the-art. The MATLAB code for generating the best ensembles in the experimental section will be available at https://github.com/LorisNanni.

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• fastai: A Layered API for Deep Learning
• Deep tree-ensembles for multi-output prediction
• LapTool-Net: A Contextual Detector of Surgical Tools in Laparoscopic Videos Based on Recurrent Convolutional Neural Networks
• Exploiting Adam-like Optimization Algorithms to Improve the Performance of Convolutional Neural Networks