An Asynchronous Recurrent Network of Cellular Automaton-Based Neurons and Its Reproduction of Spiking Neural Network Activities

Minicolumn-Based Episodic Memory Model With Spiking Neurons, Dendrites and Delays

Episodic memory is fundamental to the brain's cognitive function, but how neuronal activity is temporally organized during its encoding and retrieval is still unknown. In this article, combining hippocampus structure with a spiking neural network (SNN), a new bionic spiking temporal memory (BSTM) model is proposed to explore the encoding, formation, and retrieval of episodic memory. For encoding episodic memory, the spike-timing-dependent-plasticity (STDP) learning algorithm and a proposed minicolumn selection algorithm are used to encode each input item into several active minicolumns. For the formation of episodic memory, a sequential memory algorithm is proposed to store the contexts between items. For retrieval of episodic memory, the local retrieval algorithm and the global retrieval algorithm are proposed to retrieve sequence information, achieving multisentence prediction and multitime step prediction. All functions of BSTM are based on bionic spiking neurons, which have biological characteristics including columnar and dendritic structures, firing and receiving spikes, and delaying transmission. To test the performance of the BSTM model, the Children's Book Test (CBT) data set was used to conduct a series of experiments under different settings, including changing the number of minicolumns, neurons and sequences, modifying sequence items, etc. Compared to other sequence memory algorithms, the experimental results show that the proposed BSTM achieves higher accuracy and better robustness.

A Neuromorphic CMOS Circuit With Self-Repairing Capability

Neurophysiological observations confirm that the brain not only is able to detect the impaired synapses (in brain damage) but also it is relatively capable of repairing faulty synapses. It has been shown that retrograde signaling by astrocytes leads to the modulation of synaptic transmission and thus bidirectional collaboration of astrocyte with nearby neurons is an important aspect of self-repairing mechanism. Specifically, the retrograde signaling via astrocyte can increase the transmission probability of the healthy synapses linked to the neuron. Motivated by these findings, in the present research, a CMOS neuromorphic circuit with self-repairing capabilities is proposed based on astrocyte signaling. In this way, the computational model of self-repairing process is hired as a basis for designing a novel analog integrated circuit in the 180-nm CMOS technology. It is illustrated that the proposed analog circuit is able to successfully recompense the damaged synapses by appropriately modifying the voltage signals of the remaining healthy synapses in the wide range of frequency. The proposed circuit occupies 7500- [Formula: see text] silicon area and its power consumption is about [Formula: see text]. This neuromorphic fault-tolerant circuit can be considered as a key candidate for future silicon neuronal systems and implementation of neurorobotic and neuro-inspired circuits.

A Machine Vision-Based Pipe Leakage Detection System for Automated Power Plant Maintenance

Industrial pipework maintenance inspection can be automated through machine vision-based effusion monitoring. However, colorless effusions such as water can be difficult to detect in a complex industrial environment due to weak illumination and poor visibility of the background. This paper deploys the reflective characteristics of effusion and its lower temperature compared to the environment in order to develop an automatic inspection system for power plant pipeworks' maintenance. Such a system is aimed at detecting the colorless fluid effusion based on dual source images and a contour features algorithm. In this respect, a visible light source unit highlights the reflective features of the effusion edge. Meanwhile, high-definition images of the potential effusion are acquired under both visible and infrared lights. A customized image processing procedure extracts the potential effusion features from the infrared image to retrieve the region of interest for segmentation purposes and transfer such information to the visible light image to determine the effusion contour. Finally, a decision-making support tool based on the image contour closure is enabled for classification purposes. The implementation of the proposed system is tested on a real industrial environment. Experimental results show a classification accuracy up to 99%, demonstrating excellent suitability in meeting industrial requirements.

Data-Driven Compartmental Modeling Method for Harmonic Analysis—A Study of the Electric Arc Furnace

The electric arc furnace (EAF) contributes to almost one-third of the global iron and steel industry, and its harmonic pollution has drawn attention. An accurate EAF harmonic model is essential to evaluate the harmonic pollution of EAF. In this paper, a data-driven compartmental modeling method (DCMM) is proposed for the multi-mode EAF harmonic model. The proposed DCMM considers the coupling relationship among different frequencies of harmonics to enhance the modeling accuracy, meanwhile, the dimensions of the harmonic dataset are reduced to improve computational efficiency. Furthermore, the proposed DCMM is applicable to establish a multi-mode EAF harmonic model by dividing the multi-mode EAF harmonic dataset into several clusters corresponding to the different modes of the EAF smelting process. The performance evaluation results show that the proposed DCMM is adaptive in terms of establishing the multi-mode model, even if the data volumes, number of clusters, and sample distribution change significantly. Finally, a case study of EAF harmonic data is conducted to establish a multi-mode EAF harmonic model, showing that the proposed DCMM is effective and accurate in EAF modeling.

Cellular Automata Modeling of Stem-Cell-Driven Development of Tissue in the Nervous System

Mathematical and computational modeling enables biologists to integrate data from observations and experiments into a theoretical framework. In this review, we describe how developmental processes associated with stem-cell-driven growth of tissue in both the embryonic and adult nervous system can be modeled using cellular automata (CA). A cellular automaton is defined by its discrete nature in time, space, and state. The discrete space is represented by a uniform grid or lattice containing agents that interact with other agents within their local neighborhood. This possibility of local interactions of agents makes the cellular automata approach particularly well suited for studying through modeling how complex patterns at the tissue level emerge from fundamental developmental processes (such as proliferation, migration, differentiation, and death) at the single-cell level. As part of this review, we provide a primer for how to define biologically inspired rules governing these processes so that they can be implemented into a CA model. We then demonstrate the power of the CA approach by presenting simulations (in the form of figures and movies) based on building models of three developmental systems: the formation of the enteric nervous system through invasion by neural crest cells; the growth of normal and tumorous neurospheres induced by proliferation of adult neural stem/progenitor cells; and the neural fate specification through lateral inhibition of embryonic stem cells in the neurogenic region of Drosophila.

A Comparison of Regularization Techniques in Deep Neural Networks

Artificial neural networks (ANN) have attracted significant attention from researchers because many complex problems can be solved by training them. If enough data are provided during the training process, ANNs are capable of achieving good performance results. However, if training data are not enough, the predefined neural network model suffers from overfitting and underfitting problems. To solve these problems, several regularization techniques have been devised and widely applied to applications and data analysis. However, it is difficult for developers to choose the most suitable scheme for a developing application because there is no information regarding the performance of each scheme. This paper describes comparative research on regularization techniques by evaluating the training and validation errors in a deep neural network model, using a weather dataset. For comparisons, each algorithm was implemented using a recent neural network library of TensorFlow. The experiment results showed that an autoencoder had the worst performance among schemes. When the prediction accuracy was compared, data augmentation and the batch normalization scheme showed better performance than the others.

Conduction Delay Learning Model for Unsupervised and Supervised Classification of Spatio-Temporal Spike Patterns

Precise spike timing is considered to play a fundamental role in communications and signal processing in biological neural networks. Understanding the mechanism of spike timing adjustment would deepen our understanding of biological systems and enable advanced engineering applications such as efficient computational architectures. However, the biological mechanisms that adjust and maintain spike timing remain unclear. Existing algorithms adopt a supervised approach, which adjusts the axonal conduction delay and synaptic efficacy until the spike timings approximate the desired timings. This study proposes a spike timing-dependent learning model that adjusts the axonal conduction delay and synaptic efficacy in both unsupervised and supervised manners. The proposed learning algorithm approximates the Expectation-Maximization algorithm, and classifies the input data encoded into spatio-temporal spike patterns. Even in the supervised classification, the algorithm requires no external spikes indicating the desired spike timings unlike existing algorithms. Furthermore, because the algorithm is consistent with biological models and hypotheses found in existing biological studies, it could capture the mechanism underlying biological delay learning.