Feedforward Network Research Articles

Metaplasticity and memory in multilevel recurrent feed-forward networks

Metaplasticity and memory in multilevel recurrent feed-forward networks

Heart Sound Classification Using Harmonic and Percussive Spectral Features from Phonocardiograms with a Deep ANN Approach

Cardiovascular diseases (CVDs) are a leading cause of mortality worldwide, with a particularly high burden in India. Non-invasive methods like Phonocardiogram (PCG) analysis capture the acoustic activity of the heart. This holds significant potential for the early detection and diagnosis of heart conditions. However, the complexity and variability of PCG signals pose considerable challenges for accurate classification. Traditional methods of PCG signal analysis, including time-domain, frequency-domain, and time-frequency domain techniques, often fall short in capturing the intricate details necessary for reliable diagnosis. This study introduces an innovative approach that leverages harmonic–percussive source separation (HPSS) to extract distinct harmonic and percussive spectral features from PCG signals. These features are then utilized to train a deep feed-forward artificial neural network (ANN), classifying heart conditions as normal or abnormal. The methodology involves advanced digital signal processing techniques applied to PCG recordings from the PhysioNet 2016 dataset. The feature set comprises 164 attributes, including the Chroma STFT, Chroma CENS, Mel-frequency cepstral coefficients (MFCCs), and statistical features. These are refined using the ROC-AUC feature selection method to ensure optimal performance. The deep feed-forward ANN model was rigorously trained and validated on a balanced dataset. Techniques such as noise reduction and outlier detection were used to improve model training. The proposed model achieved a validation accuracy of 93.40% with sensitivity and specificity rates of 82.40% and 80.60%, respectively. These results underscore the effectiveness of harmonic-based features and the robustness of the ANN in heart sound classification. This research highlights the potential for deploying such models in non-invasive cardiac diagnostics, particularly in resource-constrained settings. It also lays the groundwork for future advancements in cardiac signal analysis.

Data-driven multivariate time series prediction of in-vehicle equipment failure rates

Effectively predicting the failure rate of train-controlled on-board equipment is of great significance for rationally allocating equipment spares, drawing up maintenance plans, and reducing the occurrence of failures. In order to tackle the problem of the intricate attributes and limited predictive precision of the sample data pertaining to the failure rate of on-board equipment, in this paper, a multivariate time series prediction model for the failure rate of train-controlled on-board equipment is based on the combination of multivariate variational modal decomposition (MVMD) graph neural network (GNN) and transformer. First, the original failure rate time series, air temperature, humidity and sand and dust time series are modally decomposed using MVMD, and the intrinsic modal functions (IMFs) of each series are obtained; then, the dynamic graph of the GNN network is defined according to the IMFs, and Transformer’s self-attention mechanism is utilised to capture the dynamic graph’s temporal and spatial dependencies. Finally, the failure rate is output through the feed-forward neural network prediction value. Experiments using the historical fault data of CTCS3-300T train-controlled on-board equipment are carried out to confirm the efficacy of the suggested method, and it is contrasted with other conventional machine learning techniques. The outcomes of the experiment show that compared with other train-controlled on-board equipment failure prediction models, the proposed method has a very good superiority, as evidenced by its mean absolute error (MAE) of 0.0489 and root mean square error (RMSE) of 0.0510, which is of certain reference value for equipment operation and maintenance.

Towards industry-ready additive manufacturing: AI-enabled closed-loop control for 3D melt electrowriting.

Melt electrowriting (MEW) is an emerging high-resolution 3D printing technology used in biomedical engineering, regenerative medicine, and soft robotics. Its transition from academia to industry faces challenges such as slow experimentation, low printing throughput, poor reproducibility, and user-dependent operation, largely due to the nonlinear and multiparametric nature of the MEW process. To address these challenges, we applied computer vision and machine learning to monitor and analyze the process in real-time through imaging of the MEW jet between the nozzle-collector gap. To collect data for training we developed an automated data collection methodology that eases the experimental time from days to hours. A feedforward neural network, working in concert with optimization methods and a feedback loop, is used to develop closed-loop control ensuring reproducibility of the printed parts. We demonstrate that machine learning allows streamlining the MEW operation via closed-loop control of the highly nonlinear 3D printing technology.

Machine learning for high-performance solar radiation prediction

This research paper focuses on predicting surface solar radiation for 45 glaciers situated in two locations within the northern regions of Pakistan: Khyber Pakhtunkhwa (KPK) and Gilgit. The study investigates the relationship between input parameters, including date, temperature, pressure, precipitation, and aerosol, and solar radiation output parameters. The data used for this analysis is sourced from the CERES dataset, covering the period from 2001 to 2021. The study considers eight glaciers in KPK and thirty-seven glaciers in Gilgit to provide a comprehensive understanding of the surface solar radiation patterns in these regions. Various machine learning algorithms are employed for this prediction, including linear regression (LR), decision tree (DT), random forest (RF), feed-forward neural network (FFNN), and long short-term memory (LSTM). We considered the mean squared error (MSE), mean absolute error (MAE), normal root mean squared (nRMSE), and R-squared (R2) score as the performance metrics to assess the performance of the models. The results for the KPK location indicate that the FFNN algorithm achieved the highest accuracy with an MSE of 598.326, MAE of 18.9685, nRMSE of 0.06973, and R2 score of 0.916399. Similarly, the FFNN algorithm outperformed other models for the Gilgit location with an MSE of 738.78, MAE of 20.6887, nRMSE of 0.08071, and R2 score of 0.886703. This work contributes to understanding surface solar radiation patterns in the northern regions of Pakistan, specifically in KPK and Gilgit. This research has practical implications for renewable energy planning, climate change assessments, and glacier monitoring. By accurately predicting surface solar radiation, stakeholders can make informed decisions and develop sustainable strategies for these regions.

A Unified Model for Chinese Cyber Threat Intelligence Flat Entity and Nested Entity Recognition

In recent years, as cybersecurity threats have become increasingly severe and cyberattacks have occurred frequently, higher requirements have been put forward for cybersecurity protection. Therefore, the Named Entity Recognition (NER) technique, which is the cornerstone of Cyber Threat Intelligence (CTI) analysis, is particularly important. However, most existing NER studies are limited to recognizing single-layer flat entities, ignoring the possible nested entities in CTI. On the other hand, most of the existing studies focus on English CTIs, and the existing models performed poorly in a limited number of Chinese CTI studies. Given the above challenges, we propose in this paper a novel unified model, RBTG, which aims to identify flat and nested entities in Chinese CTI effectively. To overcome the difficult boundary recognition problem and the direction-dependent and distance-dependent properties in Chinese CTI NER, we use Global Pointer as the decoder and TENER as the encoder layer, respectively. Specifically, the Global Pointer layer solves the problem of the insensitivity of general NER methods to entity boundaries by utilizing the relative position information and the multiplicative attention mechanism. The TENER layer adapts to the Chinese CTI NER task by introducing an attention mechanism with direction awareness and distance awareness. Meanwhile, to cope with the complex feature capture of hierarchical structure and dependencies among Chinese CTI nested entities, the TENER layer solves the problem by following the structure of multiple self-attention layers and feed-forward network layers superimposed on each other in the Transformer. In addition, to fill the gap in the Chinese CTI nested entity dataset, we further apply the Large Language Modeling (LLM) technique and domain knowledge to construct a high-quality Chinese CTI nested entity dataset, CDTinee, which consists of six entity types selected from STIX, including nearly 4000 entity types extracted from more than 3000 threatening sentences. In the experimental session, we conduct extensive experiments on multiple datasets, and the results show that the proposed model RBTG outperforms the baseline model in both flat NER and nested NER.

Quantification of Size-Binned Particulate Matter in Electronic Cigarette Aerosols Using Multi-Spectral Optical Sensing and Machine Learning

To monitor health risks associated with vaping, we introduce a multi-spectral optical sensor powered by machine learning for real-time characterization of electronic cigarette aerosols. The sensor can accurately measure the mass of particulate matter (PM) in specific particle size channels, providing essential information for estimating lung deposition of vaping aerosols. For the sensor’s input, wavelength-specific optical attenuation signals are acquired for three separate wavelengths in the ultraviolet, red, and near-infrared range, and the inhalation pressure is collected from a pressure sensor. The sensor’s outputs are PM mass in three size bins, specified as 100–300 nm, 300–600 nm, and 600–1000 nm. Reference measurements of electronic cigarette aerosols, obtained using a custom vaping machine and a scanning mobility particle sizer, provided the ground truth for size-binned PM mass. A lightweight two-layer feedforward neural network was trained using datasets acquired from a wide range of puffing conditions. The performance of the neural network was tested using unseen data collected using new combinations of puffing conditions. The model-predicted values matched closely with the ground truth, and the accuracy reached 81–87% for PM mass in three size bins. Given the sensor’s straightforward optical configuration and the direct collection of signals from undiluted vaping aerosols, the achieved accuracy is notably significant and sufficiently reliable for point-of-interest sensing of vaping aerosols. To the best of our knowledge, this work represents the first instance where machine learning has been applied to directly characterize high-concentration undiluted electronic cigarette aerosols. Our sensor holds great promise in tracking electronic cigarette users’ puff topography with quantification of size-binned PM mass, to support long-term personalized health and wellness.

A spatiotemporal correlation and attention-based model for pipeline deformation prediction in foundation pit engineering

In foundation pit engineering, the deformation prediction of adjacent pipelines is crucial for construction safety. Existing approaches depend on constitutive models, grey correlation prediction, or traditional feedforward neural networks. Due to the complex hydrological and geological conditions, as well as the nonstationary and nonlinear characteristics of monitoring data, this problem remains a challenge. By formulating the deformation of monitoring points as multivariate time series, a deep learning-based prediction model is proposed, which utilizes the convolutional neural network to extract the spatial dependencies among various monitoring points, and leverages the bi-directional long-short memory unit network to extract temporal features. Notably, an attention mechanism is introduced to adjust the trainable weights of spatial-temporal features extracted in the prediction. The evaluation of a real-world subway project demonstrates that the proposed model has advantages compared with current models, particularly in long-term prediction. It improves the Adjusted R2 index averagely by from 19.4 to 61.6%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} compared with existing models. The proposed model also exhibits a decrease in mean absolute error ranging from 51.5 to 70.3%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} compared to others. Experiments and analyses verify that the spatial-temporal dependencies in time series and the attention learning for spatial-temporal features can improve the prediction of such engineering problems.

Enhanced local multi-windows attention network for lightweight image super-resolution

Since the global self-attention mechanism can capture long-distance dependencies well, Transformer-based methods have achieved remarkable performance in many vision tasks, including single-image super-resolution (SISR). However, there are strong local self-similarities in images, if the global self-attention mechanism is still used for image processing, it may lead to excessive use of computing resources on parts of the image with weak correlation. Especially in the high-resolution large-size image, the global self-attention will lead to a large number of redundant calculations. To solve this problem, we propose the Enhanced Local Multi-windows Attention Network (ELMA), which contains two main designs. First, different from the traditional self-attention based on square window partition, we propose a Multi-windows Self-Attention (M-WSA) which uses a new window partitioning mechanism to obtain different types of local long-distance dependencies. Compared with original self-attention mechanisms commonly used in other SR networks, M-WSA reduces computational complexity and achieves superior performance through analysis and experiments. Secondly, we propose a Spatial Gated Network (SGN) as a feed-forward network, which can effectively overcome the problem of intermediate channel redundancy in traditional MLP, thereby improving the parameter utilization and computational efficiency of the network. Meanwhile, SGN introduces spatial information into the feed-forward network that traditional MLP cannot obtain. It can better understand and use the spatial structure information in the image, and enhances the network performance and generalization ability. Extensive experiments show that ELMA achieves competitive performance compared to state-of-the-art methods while maintaining fewer parameters and computational costs.

Infrared thermal measurement in power system considering complex circumstances

Abstract Infrared thermal measurement is a vital tool in power systems for monitoring the temperature of electrical equipment without direct contact. This non-invasive technique helps detect hot spots, identify potential issues, and evaluate the performance of power system components. However, the accuracy of the thermal measurement for power system equipment suffers from complex situations and stochastic circumstances. This paper uses a machine-learning-based method to calculate the accurate surface temperature of equipment, which is mainly based on the feedforward network and backpropagation algorithm. At the same time, multiple regression algorithms are implemented and compared. The simulation results and the experiments show that the infrared thermal measurement based on the proposed method reduces the measurement error to 0.1%.

Heat transfer study on a stator-permanent magnet electric motor: A hybrid estimation model for real-time temperature monitoring and predictive maintenance

When electrical machines operate without a specific cooling system, the surrounding environment plays a crucial role in the rise of temperature and the duty cycle of operation. More clearly, a natural convection cooling system with a low value of heat transfer coefficient carries the risk of thermal breakdown, insufficient safety, and reliability. This paper studies the heat transfer aspects of a low-power flux switching permanent magnet (FSPM) motor under natural convection cooling to implement a novel real-time sensor-less temperature monitoring system. Thermal and electromagnetic experiments are carried out to create foundations for transient and steady-state numerical models. A data-driven, deep learning algorithm estimates the core and permanent magnet (PM) eddy current losses in real-time, besides the already available copper and friction losses. Subsequently, a two-node thermal equivalent circuit in a hybrid model with a feed-forward neural network estimates the dynamic temperature profile of windings and PMs. It is indicated that the worst-case estimation error is below 7.5%, and the configuration is applicable under a wide range of operation states and environmental conditions. Lastly, the system, including the power source, FSPM motor, and hybrid temperature estimation unit, will be implemented in MATLAB/Simulink to investigate the fault prediction and operation management capabilities.

A hybrid model for accurate prediction of composite longitudinal elastic modulus

This research presents a novel hybrid model that integrates a physical-based empirical model with an Artificial Neural Network (ANN) to accurately predict the longitudinal modulus of elasticity for composites under compression. The study focuses on a composite material with a pore inclusion within an ABS plastic matrix, exploring various pore volumes, orientations, and shapes. As part of the proposed hybrid model, a regression-type neural network was trained in MATLAB® to predict and correct discrepancies between the Generalized Stiffness Formulation (GSF) homogenization-based modeling method and the collected compression experimental test results. Using MATLAB® neural network, random error datasets were used to train the feed-forward neural network, and the remaining error datasets were used for validating the performance of the proposed hybrid modeling scheme.The hybrid model demonstrated superior performance, achieving the lowest Mean Error (ME) of 0.1684864, Mean Absolute Error (MAE) of 1.051846, Mean Squared Error (MSE) of 3.500952, and highest R-squared of 0.998797. The proposed hybrid model outperformed both the Generalized Stiffness Formulation (GSF) and standalone ANN models. The significant improvement in prediction accuracy underscores the novelty and robustness of the hybrid approach in composite material modeling. Furthermore, this method can be used to refine any existing physical model by focusing on improving these established models to match experimental results and reducing the discrepancies, which offers a more efficient and attractive strategy for accurate predictions.

Seismic random noise suppression via mining multi-scale local and global information

Suppressing random noise is critical for revealing real subsurface structures. Convolutional neural networks (CNNs), the leading seismic data denoising methods, excel at extracting local features but struggle to capture global representations. Unet can extract and reuse multi-scale features, aiding in the precise detection of details and semantic information; however, being based on convolutional operations, it struggles to capture global information. To capture global representations, researchers normally employ Transformers in high-level visual tasks, owing to their self-attention mechanisms. This paper introduces a method for mining multi-scale local and global information based on hybrid-gated Unet (HGUnet), which integrates Transformer, CNN, and Unet architectures to enhance the feature representation capability for seismic random noise suppression tasks. HGUnet comprises hybrid-gated blocks (HGB) embedded within a U-shaped architecture, employing a concurrent structure of Octave convolution and lightweight multi-head self-attention mechanism to efficiently extract multi-scale local and global features simultaneously. Moreover, at the conclusion of the HGB, to precisely leverage information and reduce computing costs, a gated feedforward network is designed to retain valuable information and prune redundancies for feature fusion. Synthetic and field experimental results demonstrate that HGUnet improves denoising quality over traditional and CNN methods without adding significant computing costs.

Junction conditions for one-dimensional network hemodynamic model for total cavopulmonary connection using physically informed deep learning technique

Abstract This paper presents a novel methodology utilizing physics-informed neural network (PINN) as a junction condition for a 1D network model of blood flow in total cavopulmonary connection generated by the Fontan procedure. The technique integrates a 3D mesh generation process based on the parameterization of the junction geometry, along with a sophisticated physically regularized neural network architecture. Synthetic datasets are produced using 3D steady Stokes simulations within fixed boundaries. We use a physically informed feedforward neural network that utilizes a physically regularized loss function, which incorporates the principle of mass conservation. Our PINN achieves a tolerance of 6% on the test set. We develop a 1D-PINN multiscale model based on a previously developed method for multiscale 1D–3D simulations. Comparison with 1D–3D Stokes based model and 3D Navier–Stokes based model verifies the 1D-PINN model. In the first and second comparison, the maximum deviations of the averaged pressures and flows do not exceed 1.48% and 12.26%, respectively.

ACMamba: A State Space Model-Based Approach for Multi-Weather Degraded Image Restoration

In computer vision, eliminating the effects of adverse weather conditions such as rain, snow, and fog on images is a key research challenge. Existing studies primarily focus on image restoration for single weather types, while methods addressing image restoration under multiple combined weather conditions remain relatively scarce. Furthermore, current mainstream restoration networks, mostly based on Transformer and CNN architectures, struggle to achieve an effective balance between global receptive field and computational efficiency, limiting their performance in practical applications. This study proposes ACMamba, an end-to-end lightweight network based on selective state space models, aimed at achieving image restoration under multiple weather conditions using a unified set of parameters. Specifically, we design a novel Visual State Space Module (VSSM) and a Spatially Aware Feed-Forward Network (SAFN), which organically combine the local feature extraction capabilities of convolutions with the long-range dependency modeling capabilities of selective state space models (SSMs). This combination significantly improves computational efficiency while maintaining a global receptive field, enabling effective application of the Mamba architecture to multi-weather image restoration tasks. Comprehensive experiments demonstrate that our proposed approach significantly outperforms existing methods for both specific and multi-weather tasks across multiple benchmark datasets, showcasing its efficient long-range modeling potential in multi-weather image restoration tasks.

Various optimized artificial neural network simulations of advection-diffusion processes

The aim of this research is to describe an artificial neural network (ANN) based method to approximate the solutions of the natural advection-diffusion equations. Although the solutions of these equations can be obtained by various effective numerical methods, feed forward neural network (FFNN) techniques combined with different optimization techniques offer a more practicable and flexible alternative than the traditional approaches to solve those equations. However, the ability of FFNN techniques to solve partial differential equations is a questionable issue and has not yet been fully concluded in the existing literature. The reliability and accuracy of computational results can be advanced by the choice of optimization techniques. Therefore, this study aims to take an effective step towards presenting the ability to solve the advection-diffusion equations by leveraging the inherent benefits of ANN methods while avoiding some of the limitations of traditional approaches. In this technique, the solution process requires minimizing the error generated by using a differential equation whose solution is considered as a trial solution. More specifically, this study uses a FFNN and backpropagation technique, one of the variants of the ANN method, to minimize the error and the adjustment of parameters. In the solution process, the loss function (error) needs to be minimized; this is accomplished by fitting the trial function into the differential equation using appropriate optimization techniques and obtaining the network output. Therefore, in this study, the commonly used techniques in the literature, namely gradient descent (GD), particle swarm optimization (PSO) and artificial bee colony (ABC), are selected to compare the effectiveness of gradient and gradient-free optimization techniques in solving the advection-diffusion equation. The calculations with all three optimization techniques for linear and nonlinear advection-diffusion equations have been run several times to obtain the optimum accuracy of the results. The computed results are seen to be very promising and in good agreement with the effective numerical methods and the physics-informed neural network (PINN) method in the literature. It is also concluded that the PSO-based algorithm outperforms other methods in terms of accuracy.

Deep Learning Ensemble for Flood Probability Analysis

Predicting flood events is complex due to uncertainties from limited gauge data, high data and computational demands of traditional physical models, and challenges in spatial and temporal scaling. This research innovatively uses only three remotely sensed and computed factors: rainfall, runoff and temperature. We also employ three deep learning models—Feedforward Neural Network (FNN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM)—along with a deep neural network ensemble (DNNE) using synthetic data to predict future flood probabilities, utilizing the Savitzky–Golay filter for smoothing. Using a hydrometeorological dataset from 1993–2022 for the Nile River basin, six flood predictors were derived. The FNN and LSTM models exhibited high accuracy and stable loss, indicating minimal overfitting, while the CNN showed slight overfitting. Performance metrics revealed that FNN achieved 99.63% accuracy and 0.999886 ROC AUC, CNN had 95.42% accuracy and 0.893218 ROC AUC, and LSTM excelled with 99.82% accuracy and 0.999967 ROC AUC. The DNNE outperformed individual models in reliability and consistency. Runoff and rainfall were the most influential predictors, while temperature had minimal impact.

Reverse engineering of feedforward cortical-Hippocampal microcircuits for modelling neural network function and dysfunction

Engineered biological neural networks are indispensable models for investigation of neural function and dysfunction from the subcellular to the network level. Notably, advanced neuroengineering approaches are of significant interest for their potential to replicate the topological and functional organization of brain networks. In this study, we reverse engineered feedforward neural networks of primary cortical and hippocampal neurons, using a custom-designed multinodal microfluidic device with Tesla valve inspired microtunnels. By interfacing this device with nanoporous microelectrodes, we show that the reverse engineered multinodal neural networks exhibit capacity for both segregated and integrated functional activity, mimicking brain network dynamics. To advocate the broader applicability of our model system, we induced localized perturbations with amyloid beta to study the impact of pathology on network functionality. Additionally, we demonstrate long-term culturing of subregion- and layer specific neurons extracted from the entorhinal cortex and hippocampus of adult Alzheimer’s-model mice and rats. Our results thus highlight the potential of our approach for reverse engineering of anatomically relevant multinodal neural networks to study dynamic structure-function relationships in both healthy and pathological conditions.

Transfer learning for probabilistic localization of hidden cracks in concrete structures

AbstractThe utility of discriminative supervised learning models built using multiple training-data sources is investigated for hidden crack localization in concrete. Feed-forward neural network (FFNN) is chosen as the model architecture, and transfer learning is used to assimilate the information obtained from different sources (computational physics simulations and laboratory experiments). The labeled training data consists of values of a damage index and the known locations of hidden cracks. The classification models need to learn how the presence of damage (hidden cracks) affects the damage index at different sensors for different test conditions. To this end, diagnostic FFNN models are built by sequentially adding and training new hidden layers to assimilate labeled information from computer models (different model geometries, test conditions, crack lengths, crack locations) and laboratory experiments on a plain cement slab. These transfer learning-based models are then used to localize damage in concrete specimens that reflect real-world conditions (i.e., specimens with steel reinforcement and randomly distributed aggregate). The actual damage state in these specimens is determined by extracting cores and performing petrographic studies on the extracted cores. The damage probability estimated by transfer learning-based models is compared with the petrographic damage rating index (DRI) to identify the most suitable approach to train the diagnostic models. The transfer learning-based diagnostic methodology shows promise and could be used in various structural health monitoring applications, where sufficient labeled data are typically not available from a single data source.

Competitive plasticity to reduce the energetic costs of learning.

The brain is not only constrained by energy needed to fuel computation, but it is also constrained by energy needed to form memories. Experiments have shown that learning simple conditioning tasks which might require only a few synaptic updates, already carries a significant metabolic cost. Yet, learning a task like MNIST to 95% accuracy appears to require at least 108 synaptic updates. Therefore the brain has likely evolved to be able to learn using as little energy as possible. We explored the energy required for learning in feedforward neural networks. Based on a parsimonious energy model, we propose two plasticity restricting algorithms that save energy: 1) only modify synapses with large updates, and 2) restrict plasticity to subsets of synapses that form a path through the network. In biology networks are often much larger than the task requires, yet vanilla backprop prescribes to update all synapses. In particular in this case, large savings can be achieved while only incurring a slightly worse learning time. Thus competitively restricting plasticity helps to save metabolic energy associated to synaptic plasticity. The results might lead to a better understanding of biological plasticity and a better match between artificial and biological learning. Moreover, the algorithms might benefit hardware because also electronic memory storage is energetically costly.