Weight Update Research Articles

Neuroadaptive‐based fixed‐time control for robotic manipulators with uniform prescribed performance under unknown disturbance

AbstractAchieving faster convergence, smaller transient overshoots, and higher steady‐state tracking accuracy is essential to improve the efficiency, robustness, and applicability of robotic manipulators. This article introduces an innovative adaptive fixed‐time uniform prescribed performance controller for the manipulator facing model uncertainties and unknown disturbances. Initially, by designing a modified prescribed performance function inspired by variable superposition, this study redefines the unified prescribed performance control problem into a simplified parameter selection problem. This approach allows for the incorporation of varied performance metrics within a singular control scheme, addressing both transient and steady‐state performances concurrently without shifting control frameworks. Then, to alleviate computational demands, an adaptive neural network employing a single‐parameter weight update technique compensates for uncertainties of the manipulator dynamic model. Additionally, a disturbance observer is designed to mitigate the impact of non‐parametric disturbances. Moreover, integrating fixed‐time theory with the Lyapunov stability analysis method guarantees the convergence of all error signals to a near‐zero compact neighborhood at a fixed time. Finally, the advantages and comprehensive performance of the proposed method are confirmed by numerical simulations and real‐world experiments.

Norm Augmented Reinforcement Learning Agents With Synthesized Normative Rules

The dynamic deontic (DD) is a norm synthesis framework that extracts normative rules from reinforcement learning (RL), however it was not designed to be applied in agent coordination. This study proposes a norm augmented reinforcement learning framework (NARLF) that extends said model to include a norm deliberation mechanism for learned norms re-imputation for norm biased decision-making RL agents. This study aims to test the effects of synthesized norms applied on-line and off-line on agent learning performance. The framework consists of the DD framework extended with a pre-processing and deliberation component to allow re-imputation of normative rules. A deliberation model, the Norm Augmented Q-Table (NAugQT), is proposed to map normative rules into RL agents via q-values weight updates. Results show that the framework is able to map and improve RL agent's performance but only when synthesized off-line edited absolute norm salience value norms are used. This shows limitations when unstable salience norms are applied. Improvement in norm extraction and pre-processing are required.

Power-enhanced residual network for function approximation and physics-informed inverse problems

In this study, we investigate how the updating of weights during forward operation and the computation of gradients during backpropagation impact the optimization process, training procedure, and overall performance of the neural network, particularly the multi-layer perceptrons (MLPs). This paper introduces a novel neural network structure called the Power-Enhancing residual network, inspired by highway network and residual network, designed to improve the network's capabilities for both smooth and non-smooth functions approximation in 2D and 3D settings. By incorporating power terms into residual elements, the architecture enhances the stability of weight updating, thereby facilitating better convergence and accuracy. The study explores network depth, width, and optimization methods, showing the architecture's adaptability and performance advantages. Consistently, the results emphasize the exceptional accuracy of the proposed Power-Enhancing residual network, particularly for non-smooth functions. Real-world examples also confirm its superiority over plain neural network in terms of accuracy, convergence, and efficiency. Moreover, the proposed architecture is also applied to solving the inverse Burgers' equation, demonstrating superior performance. In conclusion, the Power-Enhancing residual network offers a versatile solution that significantly enhances neural network capabilities by emphasizing the importance of stable weight updates for effective training in deep neural networks. The codes implemented are available at: https://github.com/CMMAi/ResNet_for_PINN.

Lifelong reinforcement learning tracking control of nonlinear strict-feedback systems using multilayer neural networks with constraints

This paper presents a novel safe integral reinforcement learning (IRL)-based optimal trajectory tracking scheme for nonlinear systems with uncertain dynamics that is subject to constraints. We leverage multilayer neural networks (MNNs) for actor-critic MNNs along with an NN identifier in the backstepping process for minimizing a discounted value function. A time-varying barrier Lyapunov function (TVBLF) is utilized for handling constraints and to provide safety assurances. Online weight update laws for the actor and critic MNNs are derived that are driven by Bellman error and control input error. We introduce an online lifelong learning (LL) method in the critic NN, utilizing the Bellman error in MNNs to address catastrophic forgetting. The method’s effectiveness is demonstrated through simulations on mobile robot multitask tracking. The paper concludes with a stability analysis of the closed-loop system.

An attention mechanism network based on the winner-take-all

In the field of neurology, neurons compete for brain attention in winner-take-all (WTA) competitions. Inspired by this, we propose a new WTA-based attention network (called ANW), which can be extended to general neural networks. The ANW network simulates WTA behavior in biological neurons; that is, the winner neuron itself becomes excited and sends its own spike signal. Furthermore, the winner will output an inhibition signal, which will be input into the cell synapses of other neurons. The ANW network regards the update of neuron weights after backpropagation as a stimulus input to neurons. Combined with the WTA function, the neural network will continue to update until it reaches a stable state. In this way, the ANW network can find the most active neurons in the network and generate the winners among these neurons to improve the ability of the neural network to extract features. As the ANW is a small and universal network, it can be seamlessly inserted into any neural network architecture, with negligible overhead, and can be trained together with a basic CNN. We verified the neural network with ANW by using the ImageNet-100, CIFAR-100 and MS COCO detection datasets for the experiments. The experimental results show that, compared with those of the baseline network, the top-1 err gains of 0.63% and 3.85% can be achieved for ANW, with classical ResNet-50 as the backbone network, respectively, demonstrating that the method can improve the performance of the model in image classification and target detection with wide applicability. The proposed method provides an effective, and almost consumption-neutral solution, for performance improvement in the field of computer vision target detection.

A deep transfer learning model for the deformation of braced excavations with limited monitoring data

The current deep learning models for braced excavation cannot predict deformation from the beginning of excavation due to the need for a substantial corpus of sufficient historical data for training purposes. To address this issue, this study proposes a transfer learning model based on a sequence-to-sequence two-dimensional (2D) convolutional long short-term memory neural network (S2SCL2D). The model can use the existing data from other adjacent similar excavations to achieve wall deflection prediction once a limited amount of monitoring data from the target excavation has been recorded. In the absence of adjacent excavation data, numerical simulation data from the target project can be employed instead. A weight update strategy is proposed to improve the prediction accuracy by integrating the stochastic gradient masking with an early stopping mechanism. To illustrate the proposed methodology, an excavation project in Hangzhou, China is adopted. The proposed deep transfer learning model, which uses either adjacent excavation data or numerical simulation data as the source domain, shows a significant improvement in performance when compared to the non-transfer learning model. Using the simulation data from the target project even leads to better prediction performance than using the actual monitoring data from other adjacent excavations. The results demonstrate that the proposed model can reasonably predict the deformation with limited data from the target project.

Bio-Inspired Hyperparameter Tuning of Federated Learning for Student Activity Recognition in Online Exam Environment

Nowadays, online examination (exam in short) platforms are becoming more popular, demanding strong security measures for digital learning environments. This includes addressing key challenges such as head pose detection and estimation, which are integral for applications like automatic face recognition, advanced surveillance systems, intuitive human–computer interfaces, and enhancing driving safety measures. The proposed work holds significant potential in enhancing the security and reliability of online exam platforms. It achieves this by accurately classifying students’ attentiveness based on distinct head poses, a novel approach that leverages advanced techniques like federated learning and deep learning models. The proposed work aims to classify students’ attentiveness with the help of different head poses. In this work, we considered five head poses: front face, down face, right face, up face, and left face. A federated learning (FL) framework with a pre-trained deep learning model (ResNet50) was used to accomplish the classification task. To classify students’ activity (behavior) in an online exam environment using the FL framework’s local client device, we considered the ResNet50 model. However, identifying the best hyperparameters in the local client ResNet50 model is challenging. Hence, in this study, we proposed two hybrid bio-inspired optimized methods, namely, Particle Swarm Optimization with Genetic Algorithm (PSOGA) and Particle Swarm Optimization with Elitist Genetic Algorithm (PSOEGA), to fine-tune the hyperparameters of the ResNet50 model. The bio-inspired optimized methods employed in the ResNet50 model will train and classify the students’ behavior in an online exam environment. The FL framework trains the client model locally and sends the updated weights to the server model. The proposed hybrid bio-inspired algorithms outperform the GA and PSO when independently used. The proposed PSOGA not only outperforms the proposed PSOEGA but also outperforms the benchmark algorithms considered for performance evaluation by giving an accuracy of 95.97%.

Application of multifunctional artificial synapse Cs2AgBiBr6 in pain simulation, Pavlov learning, letter learning and number recognition

Artificial synapses combined with artificial neural networks can develop next-generation computer framework. This computer framework has the characteristics of low energy consumption, high density, self-learning and self-storage. We designed and prepared artificial synapse based on all-inorganic perovskite Cs2AgBiBr6 (CABB). This work studies the synaptic excitatory behavior of CABB synapses in neurology. By applying electrical spikes, it can exhibit excitatory behaviors similar to biological synapses. On this basis, using its synaptic excitement, we simulated some conceived functions of human-like artificial intelligence, including pain simulation, Pavlov learning, letter learning and number recognition. After testing, it can be found that CABB synapse can complete these tasks. In order to realize number recognition, we designed a multi-layer neural network according to the weight update method of CABB synapse. It shows a recognition accuracy of 91.57 %.

Reinforced deep learning approach for analyzing spaceborne-derived crop phenology

Vegetation Index (VI) curves capture the crop-specific phenological events from multi-temporal Earth observation images. Although advanced machine learning classifiers are the existing state-of-the-art, most of them assume the samples to be independent and identically distributed, which is not true for VI curve classification. This research proposed the consideration of spatial non-stationarity for VI curve-based crop classification. The proposed approach does not assume the samples to be independent and identically distributed. Different state-of-the-art approaches attempted to solve this problem by introducing architectural variations and considering the neighborhood patches. However, the inherent nature of the problem demanded an online approach. In the current research, this problem is formulated in a reinforcement learning framework where the generalizability of the predictor is improved using a feedback system. Different approaches for feedback were investigated in this study. The predictor was composed of a graph convolutional framework where the VI curves were transformed into a graph representation, incorporating the spatial, spectral, and temporal context. Graph convolutional operations were then used to learn the embedded representations and assign labels to the unlabeled points based on the labeled ones in the proximity. Further, a semi-supervised strategy was proposed where some initial feedback was employed to improve the generalizability of the model. Additionally, neighborhood-based feedback was also considered. The experiments using the VI curves collected over three farms in Israel covering wheat, potato, and barley crops illustrated the need for accounting the spatial non-stationarity in VI curve classification. The proposed dynamic feedback system and the graph-based strategy to consider spatial heterogeneity significantly improved the accuracy of the proposed framework. Additionally, the proposed reinforcement learning strategy ensures the dynamic refinement of model weights to facilitate the real-time applications even when the target data varies significantly. Although the proposed approach is generic, the end-to-end framework, as adopted in this research, is suitable for aerial or agricultural datasets. Hence, further fine tuning and remodeling may be required for non-agriculture or non-spatial datasets. However, the dynamic weight update may be adopted for any applications irrespective of the datasets.

A tolerance index based non-cooperative behaviour managing method with minimum cost in social network group decision making

This paper introduces a novel consensus theoretical framework designed to effectively manage non-cooperative behaviour in social network group decision making (SNGDM). It addresses the challenge by considering both individuals’ willingness to adjust preferences and the associated costs of achieving consensus. To deal with this issue, the personalised individual semantics (PIS) model is employed to handle original evaluation matrices by converting linguistic terms into numerical values based on experts’ personalised opinions. Subsequently, a tolerance index (TI) is defined to reflect the willingness of experts to adjust their preferences. An improved minimum cost (MC) feedback model based on TI is established. The novelty of the proposed approach is that its integration of individual preference adjustment willingness and consensus efficiency, effectively preventing groupthink. In addition, a maximum group consensus degree optimisation model is proposed to detect non-cooperative behaviour of experts. To ensure an optimal solution for the minimum cost feedback model, a weight update method is proposed, considering the trust relationship between experts. A detailed analysis regarding the selection of tolerance thresholds to prevent over-penalisation of weights of non-collaborators is reported. Finally, comprehensive numerical and comparative analyses are presented to validate the proposed method.

Intuitionistic Fuzzy Gram-Schmidt Orthogonalized Artificial Neural Network for Solving MAGDM Problems

Objectives: To propose a suitable decision-making model based on Intuitionistic Fuzzy sets (IFSs) and Gram-Schmidt orthogonalization process for Artificial Neural Network (ANN). Methods: The IFS data sets appearing in the form of matrices are aggregated using the available aggregation operators in the literature and then the collective aggregated information is processed through Gram-Schmidt orthogonalization for the revised input vectors which is then fed into the ANN algorithm following Delta Learning Rule for the next phase. The weight updation is performed through the ANN and the output is improvised. Findings: The proposed Gram-Scmidt Orthogonalization process is utilized in Intuitionistic Fuzzy Artificial Neural Network model. The Delta learning rule is utilized in the process of the Neural Network, where the Intuitionistic Fuzzy nature of the input data is transformed into a fuzzy data and then the ranking of the alternatives is done based on the weights updation through the learning phase of the ANN. Once the vector is trained out of the learning phase, it is then processed through the activation function for the final selection of the best alternative required of the Multiple Attribute Group Decision Making (MAGDM) problem posed in this work. To demonstrate the usefulness and applicability of this new method with the Gram-Schmidt process, the numerical example also adds more insight to the proposed methodology of ANN with the application of some Linear Space techniques. Novelty: Most of the research done on Intuitionistic Fuzzy Artificial Neural Network model are based on learning rules or using some other calculations. The proposed Gram-Schmidt Orthogonalization process is used to find the orthogonal basis that are used as input training vectors in the Delta learning rule for ANN. Keywords: MAGDM, ANN, Aggregation operators, Learning Rules, Intuitionistic Fuzzy sets, Gram-Scmidt Orthogonalization

A Study on h‐BN Resistive Switching Temporal Response

AbstractPrevious work that studied hexagonal boron nitride (h‐BN) memristor DC resistive‐switching characteristics is extended to include an experimental understanding of their dynamic behavior upon programming or synaptic weight update. The focus is on the temporal resistive switching response to driving stimulus (programming voltage pulses) effecting conductance updates during training in neural network crossbar implementations. Test arrays are fabricated at the wafer level, enabled by the transfer of CVD‐grown few‐layer (8 layer) or multi‐layer (18 layer) h‐BN films. A comprehensive study of their temporal response under various conditions–voltage pulse amplitude, edge rate (pulse rise/fall times), and temperature–provides new insights into the resistive switching process toward optimized devices and improvements in their implementation of artificial neural networks. The h‐BN memristors can achieve multi‐state operation through ultrafast pulsed switching (< 25 ns) with high energy efficiency (≈10 pJ pulse−1).

Reconfigurable Resistive Switching Memory for Telegraph Code Sensing and Recognizing Reservoir Computing Systems.

Reservoir computing (RC) system is based upon the reservoir layer, which non-linearly transforms input signals into high-dimensional states, facilitating simple training in the readout layer-a linear neural network. These layers require different types of devices-the former demonstrated as diffusive memristors and the latter prepared as drift memristors. The integration of these components can increase the structural complexity of RC system. Here, a reconfigurable resistive switching memory (RSM) capable of implementing both diffusive and drift dynamics is demonstrated. This reconfigurability is achieved by preparing a medium with a 3D ion transport channel (ITC), enabling precise control of the metal filament that determines memristor operation. The 3D ITC-RSM operates in a volatile threshold switching (TS) mode under a weak electric field and exhibits short-term dynamics that are confirmed to be applicable as reservoir elements in RC systems. Meanwhile, the 3D ITC-RSM operates in a non-volatile bipolar switching (BS) mode under a strong electric field, and the conductance modulation metrics forming the basis of synaptic weight update are validated, which can be utilized as readout elements in the readout layer. Finally, an RC system is designed for the application of reconfigurable 3D ITC-RSM, and performs real-time recognition on Morse code datasets.

Adapt-cMolGPT: A Conditional Generative Pre-Trained Transformer with Adapter-Based Fine-Tuning for Target-Specific Molecular Generation.

Small-molecule drug design aims to generate compounds that target specific proteins, playing a crucial role in the early stages of drug discovery. Recently, research has emerged that utilizes the GPT model, which has achieved significant success in various fields to generate molecular compounds. However, due to the persistent challenge of small datasets in the pharmaceutical field, there has been some degradation in the performance of generating target-specific compounds. To address this issue, we propose an enhanced target-specific drug generation model, Adapt-cMolGPT, which modifies molecular representation and optimizes the fine-tuning process. In particular, we introduce a new fine-tuning method that incorporates an adapter module into a pre-trained base model and alternates weight updates by sections. We evaluated the proposed model through multiple experiments and demonstrated performance improvements compared to previous models. In the experimental results, Adapt-cMolGPT generated a greater number of novel and valid compounds compared to other models, with these generated compounds exhibiting properties similar to those of real molecular data. These results indicate that our proposed method is highly effective in designing drugs targeting specific proteins.

The Impact of Weight Shifts on Inflation: Evidence for the Euro Area HICP

Shifts in household consumption feed into euro area inflation via the annual updating of product weights. The partial effect of weight changes on inflation is not quantified by statistical offices. We therefore propose a decomposition of the inflation rate, measured by the annual percentage change of the Harmonised Index of Consumer Prices (HICP), into the overall price change assuming weights at the previous year’s level and a weighting effect. We discuss this decomposition against a decomposition into pure price change and quantity effects. Our empirical results show that euro area inflation has been noticeably impacted by weighting effects since 2021. Before 2022, we observe a close relationship between weighting and quantity effects. As weighting effects can be calculated without delay from publicly available HICP data, we argue that this decomposition is relevant in terms of providing timely information for analysts and monetary policymakers.

Whole-Tree Green Density Equations for Loblolly and Slash Pine Trees

Abstract Using extensive legacy and new datasets, two equations of whole-tree green density, defined as the ratio of the green weight of stem wood with bark (GWob) divided either by the stem outside-bark volume (Vob) or by the stem inside-bark volume (Vib), were developed along with individual tree Vob, Vib, and GWob equations for loblolly and slash pines. The green density equations indicated that the GWob/Vob ratio increases while the GWob/Vib ratio decreases with an increase in tree size for both species. The transition from low-intensity management to intensive management has a notable impact on tree green weight characteristics. Generally, trees from older established plantations exhibited a higher GWob/Vob ratio compared with trees from more recently established plantations, spanning both loblolly and slash pines. Study Implications: Derived whole-tree green density equations, alongside updated stem green weight and volume equations, are valuable tools for estimating the volume and green weight of entire stem boles, facilitating volume-to-green-weight conversion for specific sections for loblolly and slash pines, the primary commercial timber species in the southern United States.

Reliable Low-Current and Multilevel Memristive Electrochemical Neuromorphic Devices with Semi-Metal Sb Filament.

Memristors are used in artificial neural networks owing to their exceptional integration capabilities and scalability. However, traditional memristors are hampered by limited resistance states and randomness, which curtails their application. The migration of metal ions critically influences the number of conductance states and the linearity of weight updates. Semi-metal filaments can provide subquantum conductance changes to the memristors due to the smaller single-atom conductance, such as Sb (≈0.01 G0 = 7.69 × 10-7 S). Here, a memristor featuring an active electrode composed of semi-metal Sb is introduced for the first time. This memristor demonstrates precise conductance control, a large on/off ratio, consistent switching, and prolonged retention exceeding 105 s. Density functional theory (DFT) calculations and characterization methods reveal the formation of Sb filaments during a set process. The interaction between Sb and O within the dielectric layer facilitates the Sb filaments' ability to preserve their morphology in the absence of electric fields.

A faster deep graph clustering network based on dynamic graph weight update mechanism

A faster deep graph clustering network based on dynamic graph weight update mechanism

Multiple feedback recurrent neural network based super-twisting predefined-time nonsingular terminal sliding mode control for quad-rotor UAV

This research deals with the overall predefined-time stability (PTS) of Unmanned Aerial Vehicles (UAV) ensuring rapid convergence based on a novel sliding mode control (SMC). The strength of predefined-time sliding manifolds lies in the convergence rate can be adjusted by an explicit parameter. For the limitation of chattering encountered by predefined-time SMC (PTSMC), a variable gain super-twisting algorithm (STA) with additional linear items is designed as the switch controller. To conserve the restrained computational resources of quadrotors, the equivalent control input is approximated by a multiple feedback recurrent neural network (MFRNN) directly, which is challenging for general recurrent neural networks. The proposed MFRNN is characterized by the incorporation of double-loop feedback within the layers, augmenting its capacity for accurate approximation. To address the vanishing gradients commonly encountered with traditional activation functions, LeakyRelu is chosen. The Lyapunov theory is utilized to ensure the PTS of overall system and obtain the MFRNN weight update laws. An experiment is conducted to validate the proposed scheme.

Stream label distribution learning processing via broad learning system

Label distribution learning (LDL) is designed for label ambiguity problem which widely exists in tasks like image classification and sentiment analysis. Nevertheless, most existing LDL methods adopt a batch-wise processing strategy that is not applicable to stream data issues, like video semantic segmentation and object tracking in auto-driving applications. For these scenarios where dynamic new data is generated continuously, stream LDL processing can be applied to reflect the changes in time and improve the accuracy of online prediction. This paper proposes a novel broad learning system (BLS) based online label distribution learning framework (SLD_BLS). Broad learning system was adopted as the baseline model because its incremental weight updating scheme, excellent efficiency, and outstanding performance can process streaming data in dynamically changing environments. However, there are several challenges to adapt BLS for LDL: 1) BLS's update rule cannot process LDL data; 2) BLS cannot show the mapping relationship between feature space and label space; 3) BLS neglects the inter-label relationships. To tackle these challenges, 1) a new weight update rule for LDL is designed; 2) a manifold regularization is applied to exploit the feature space manifolds; 3) an explicit label collaborating approach is introduced to positively bootstrapping the model training. Extensive experiments on 13 label distribution datasets indicated the performance of SLD_BLS outperforms 9 state-of-the-art LDL models on most datasets with significant reductions in training time across 6 metrics.