Broad Learning With Reinforcement Learning Signal Feedback: Theory and Applications

Broad Multitask Learning System With Group Sparse Regularization

The broad learning system (BLS) featuring lightweight, incremental extension, and strong generalization capabilities has been successful in its applications. Despite these advantages, BLS struggles in multitask learning (MTL) scenarios with its limited ability to simultaneously unravel multiple complex tasks where existing BLS models cannot adequately capture and leverage essential information across tasks, decreasing their effectiveness and efficacy in MTL scenarios. To address these limitations, we proposed an innovative MTL framework explicitly designed for BLS, named group sparse regularization for broad multitask learning system using related task-wise (BMtLS-RG). This framework combines a task-related BLS learning mechanism with a group sparse optimization strategy, significantly boosting BLS's ability to generalize in MTL environments. The task-related learning component harnesses task correlations to enable shared learning and optimize parameters efficiently. Meanwhile, the group sparse optimization approach helps minimize the effects of irrelevant or noisy data, thus enhancing the robustness and stability of BLS in navigating complex learning scenarios. To address the varied requirements of MTL challenges, we presented two additional variants of BMtLS-RG: BMtLS-RG with sharing parameters of feature mapped nodes (BMtLS-RGf), which integrates a shared feature mapping layer, and BMtLS-RGf and enhanced nodes (BMtLS-RGfe), which further includes an enhanced node layer atop the shared feature mapping structure. These adaptations provide customized solutions tailored to the diverse landscape of MTL problems. We compared BMtLS-RG with state-of-the-art (SOTA) MTL and BLS algorithms through comprehensive experimental evaluation across multiple practical MTL and UCI datasets. BMtLS-RG outperformed SOTA methods in 97.81% of classification tasks and achieved optimal performance in 96.00% of regression tasks, demonstrating its superior accuracy and robustness. Furthermore, BMtLS-RG exhibited satisfactory training efficiency, outperforming existing MTL algorithms by 8.04-42.85 times.

An Incremental-Self-Training-Guided Semi-Supervised Broad Learning System

The broad learning system (BLS) has recently been applied in numerous fields. However, it is mainly a supervised learning system and thus not suitable for specific practical applications with a mixture of labeled and unlabeled data. Despite a manifold regularization-based semi-supervised BLS, its performance still requires improvement, because its assumption is not always applicable. Therefore, this article proposes an incremental-self-training-guided semi-supervised BLS (ISTSS-BLS). Distinctive to traditional self-training, where all unlabeled data are labeled simultaneously, incremental self-training (IST) obtains unlabeled data incrementally from an established sorted list based on the distance between the data and their cluster center. During iterative learning, a small portion of labeled data is first used to train BLS. The system recursively self-updates its structure and meta-parameters using: 1) the double-restricted mechanism and 2) the dynamic neuron-incremental mechanism. The double-restricted mechanism is beneficial to preventing the introduction of incorrect pseudo-labeled samples, and the dynamic neuron-incremental mechanism guides the self-updating of the network structure effectively based on the training accuracy of the labeled data. These strategies guarantee a parsimonious model during the update. Besides, a novel metric, the accuracy-time ratio (A/T), is proposed to evaluate the model's performance comprehensively regarding time and accuracy. In experimental verifications, ISTSS-BLS performs outstandingly on 11 datasets. Specifically, the IST is compared with the traditional one on three scales data, saving up to 52.02% learning time. In addition, ISTSS-BLS is compared with different state-of-the-art alternatives, and all results indicate that it possesses significant advantages in performance.

Bidimensionally partitioned online sequential broad learning system for large-scale data stream modeling

Incremental broad learning system (IBLS) is an effective and efficient incremental learning method based on broad learning paradigm. Owing to its streamlined network architecture and flexible dynamic update scheme, IBLS can achieve rapid incremental reconstruction on the basis of the previous model without the entire retraining from scratch, which enables it adept at handling streaming data. However, two prominent deficiencies still persist in IBLS and constrain its further promotion in large-scale data stream scenarios. Firstly, IBLS needs to retain all historical data and perform associated calculations in the incremental learning process, which causes its computational overhead and storage burden to increase over time and as such puts the efficacy of the algorithm at risk for massive or unlimited data streams. Additionally, due to the random generation rule of hidden nodes, IBLS generally necessitates a large network size to guarantee approximation accuracy, and the resulting high-dimensional matrix calculation poses a greater challenge to the updating efficiency of the model. To address these issues, we propose a novel bidimensionally partitioned online sequential broad learning system (BPOSBLS) in this paper. The core idea of BPOSBLS is to partition the high-dimensional broad feature matrix bidimensionally from the aspects of instance dimension and feature dimension, and consequently decompose a large least squares problem into multiple smaller ones, which can then be solved individually. By doing so, the scale and computational complexity of the original high-order model are substantially diminished, thus significantly improving its learning efficiency and usability for large-scale complex learning tasks. Meanwhile, an ingenious recursive computation method called partitioned recursive least squares is devised to solve the BPOSBLS. This method exclusively utilizes the current online samples for iterative updating, while disregarding the previous historical samples, thereby rendering BPOSBLS a lightweight online sequential learning algorithm with consistently low computational costs and storage requirements. Theoretical analyses and simulation experiments demonstrate the effectiveness and superiority of the proposed algorithm.

Industrial Process Monitoring Based on Dynamic Overcomplete Broad Learning Network

Most industrial processes feature high nonlinearity, non-Gaussianity, and time correlation. Models based on overcomplete broad learning system (OBLS) have been successfully applied in the fault monitoring realm, which may relatively deal with the nonlinear and non-Gaussian characteristics. However, these models barely take time correlation into full consideration, hindering the further improvement of the monitoring accuracy of the network. Therefore, an effective dynamic overcomplete broad learning system (DOBLS) based on matrix extension is proposed, which extends the raw data in the batch process with the idea of "time lag" in this article. Subsequently, the OBLS monitoring network is employed to continue the analysis of the extended dynamic input data. Finally, a monitoring model is established to tackle the coexistence of nonlinearity, non-Gaussianity, and time correlation in process data. To illustrate the superiority and feasibility, the proposed model is conducted on the penicillin fermentation simulation platform, the experimental result of which illustrates that the model can extract the feature of process data more comprehensively and be self-updated more efficiently. With shorter training time and higher monitoring accuracy, the proposed model can witness an improvement of average monitoring accuracy by 3.69% and 1.26% in 26 process fault types compared to the state-of-the-art fault monitoring methods BLS and OBLS, respectively.

Distributed Neural Networks Training for Robotic Manipulation With Consensus Algorithm

In this article, we propose an algorithm that combines actor-critic-based off-policy method with consensus-based distributed training to deal with multiagent deep reinforcement learning problems. Specifically, convergence analysis of a consensus algorithm for a type of nonlinear system with a Lyapunov method is developed, and we use this result to analyze the convergence properties of the actor training parameters and the critic training parameters in our algorithm. Through the convergence analysis, it can be verified that all agents will converge to the same optimal model as the training time goes to infinity. To validate the implementation of our algorithm, a multiagent training framework is proposed to train each Universal Robot 5 (UR5) robot arm to reach the random target position. Finally, experiments are provided to demonstrate the effectiveness and feasibility of the proposed algorithm.