Convolutional Extreme Learning Machines: A Systematic Review

Abstract

Much work has recently identified the need to combine deep learning with extreme learning in order to strike a performance balance with accuracy, especially in the domain of multimedia applications. When considering this new paradigm—namely, the convolutional extreme learning machine (CELM)—we present a systematic review that investigates alternative deep learning architectures that use the extreme learning machine (ELM) for faster training to solve problems that are based on image analysis. We detail each of the architectures that are found in the literature along with their application scenarios, benchmark datasets, main results, and advantages, and then present the open challenges for CELM. We followed a well-structured methodology and established relevant research questions that guided our findings. Based on 81 primary studies, we found that object recognition is the most common problem that is solved by CELM, and CCN with predefined kernels is the most common CELM architecture proposed in the literature. The results from experiments show that CELM models present good precision, convergence, and computational performance, and they are able to decrease the total processing time that is required by the learning process. The results presented in this systematic review are expected to contribute to the research area of CELM, providing a good starting point for dealing with some of the current problems in the analysis of computer vision based on images.

A Review on Large-Scale Data Processing with Parallel and Distributed Randomized Extreme Learning Machine Neural Networks

“…The authors conclude that ELM models greatly improve the accuracy of sales forecasts compared to traditional techniques, so they suggest further research and studies with real data. In Rodrigues et al [22], a systematic review is presented on the alternative architectures of convolutional ELM (CELM), a combination of deep learning and ELM networks. The authors focus their study on the solution of problems based on image analysis and highlight that CELM models present good accuracy, convergence, and computational performance.…”

A framework for robotic arm pose estimation and movement prediction based on deep and extreme learning models

“…The second part of the proposed new model, responsible for the inference in keypoints detection, uses ELM to improve the detection of poses of the robotic arm. According to a survey carried out by Rodrigues et al [11], ELM can be used together with CNNs to improve the results in classification tasks and pretrained CNNs can be used for feature extraction. ELM models were trained with the extracted features, providing better accuracy results compared to using only CNNs.…”

“…In this work, we also demonstrate the efficacy of using SCConvs for regression tasks. In addition, we improve pose estimation through the use of the extreme learning machine (ELM) neural network [10], which when combined with CNN models tends to provide a better learning outcome [11]. 2.…”

Visual Radial Basis Q-Network

“…Other sparse representations, such as extreme machine learning or sparse coding, have been investigated but none have been extended to visual RL as their computing cost tends grows exponentially with the input dimension. One solution in the literature is to reduce the inputs dimension with convolution [21,28].…”