Search Results (52)

Contemporary neural and generative architectures are deficient in self-preservation mechanisms and sustainable stability. In uncertain or noisy situations, they frequently demonstrate oscillatory learning, overconfidence, and structural deterioration, indicating a lack of biological regulatory principles in artificial systems. We present Bio-RegNet, a meta-homeostatic Bayesian neural network architecture that integrates T-regulatory-cell-inspired immunoregulation with autophagic structural optimization. The model integrates three synergistic subsystems: the Bayesian Effector Network (BEN) for uncertainty-aware inference, the Regulatory Immune Network (RIN) for Lyapunov-based inhibitory control, and the Autophagic Optimization Engine (AOE) for energy-efficient regeneration, thereby establishing a closed energy–entropy loop that attains adaptive equilibrium among cognition, regulation, and metabolism. This triadic feedback achieves meta-homeostasis, transforming learning into a process of ongoing self-stabilization instead of static optimization. Bio-RegNet routinely outperforms state-of-the-art dynamic GNNs across twelve neuronal, molecular, and macro-scale benchmarks, enhancing calibration and energy efficiency by over 20% and expediting recovery from perturbations by 14%. Its domain-invariant equilibrium facilitates seamless transfer between biological and manufactured systems, exemplifying a fundamental notion of bio-inspired, self-sustaining intelligence—connecting generative AI and biomimetic design for sustainable, living computation. Bio-RegNet consistently outperforms the strongest baseline HGNN-ODE, improving ARI from 0.77 to 0.81 and NMI from 0.84 to 0.87, while increasing equilibrium coherence $\kappa$ from 0.86 to 0.93. Full article

The widespread application of organoids in disease modeling and drug development is significantly constrained by challenges in automated quantitative analysis. In bright-field microscopy images, organoids exhibit complex characteristics, including irregular morphology, blurred boundaries, and substantial scale variations, largely stemming from their dynamic self-organization that mimics in vivo tissue development. Existing convolutional neural network-based methods are limited by fixed receptive fields and insufficient modeling of inter-channel relationships, making them inadequate for detecting such evolving biological structures. To address these challenges, we propose a novel detection head, termed Interactive Dual-Perception Head (IDP-Head), inspired by hierarchical perception mechanisms in the biological visual cortex. Integrated into the RTMDet framework, IDP-Head comprises two bio-inspired components: a Large-Kernel Global Perception Module (LGPM) to capture global morphological dependencies, analogous to the wide receptive fields of cortical neurons, and a Progressive Channel Synergy Module (PCSM) that models inter-channel semantic collaboration, echoing the integrative processing of multi-channel stimuli in neural systems. Additionally, we construct a new organoid detection dataset to mitigate the scarcity of annotated data. Extensive experiments on both our dataset and public benchmarks demonstrate that IDP-Head achieves a 5-percentage-point improvement in mean Average Precision (mAP) over the baseline model, offering a biologically inspired and effective solution for high-fidelity organoid detection. Full article

Threshold-switching memristors (TSMs) are emerging as key enablers for hardware spiking neural networks, offering intrinsic spiking dynamics, sub-pJ energy consumption, and nanoscale footprints ideal for brain-inspired computing at the edge. This review provides a comprehensive examination of how TSMs emulate diverse spiking behaviors—including oscillatory, leaky integrate-and-fire (LIF), Hodgkin–Huxley (H-H), and stochastic dynamics—and how these features enable compact, energy-efficient neuromorphic systems. We analyze the physical switching mechanisms of redox and Mott-type TSMs, discuss their voltage-dependent dynamics, and assess their suitability for spike generation. We review memristor-based neuron circuits regarding architectures, materials, and key performance metrics. At the system level, we summarize bio-inspired neuromorphic platforms integrating TSM neurons with visual, tactile, thermal, and olfactory sensors, achieving real-time edge computation with high accuracy and low power. Finally, we critically examine key challenges—such as stochastic switching origins, device variability, and endurance limits—and propose future directions toward reconfigurable, robust, and scalable memristive neuromorphic architectures. Full article

In the era of artificial intelligence, the demand for rapid and efficient data processing is growing, and traditional computing architectures are increasingly struggling to meet these needs. Against this backdrop, memristor devices, capable of mimicking the computational functions of brain neural networks, have emerged as key components in neuromorphic systems. Despite this, memristors still face many challenges in biomimetic functionality and circuit integration. In this context, a starch–glycerol-based hydrogel memristor was developed using starch as the dielectric material. The starch–glycerol–water mixture employed in this study has been widely recognized in literature as a physically cross-linked hydrogel system with a three-dimensional network, and both high water content and mechanical flexibility. This memristor demonstrates a high current switching ratio and stable threshold voltage, showing great potential in mimicking the activity of biological neurons. The device possesses the functionality of auditory neurons, not only achieving artificial spiking neuron discharge but also accomplishing the spatiotemporal summation of input information. In addition, we demonstrate the application capabilities of this artificial auditory neuron in gain modulation and in the synchronization detection of sound signals, further highlighting its potential in neuromorphic engineering applications. These results suggest that starch-based hydrogel memristors offer a promising platform for the construction of bio-inspired auditory neuron circuits and flexible neuromorphic systems. Full article

Motion direction detection is an essential task for both computer vision and neuroscience. Inspired by the biological theory of the human visual system, we proposed a learnable horizontal-cell-based dendritic neuron model (HCdM) that captures motion direction with high efficiency while remaining highly robust. Unlike present deep learning models, which rely on extension of computation and extraction of global features, the HCdM mimics the localized processing of dendritic neurons, enabling efficient motion feature integration. Through synaptic learning that prunes unnecessary parts, our model maintains high accuracy in noised images, particularly against salt-and-pepper noise. Experimental results show that the HCdM reached over 99.5% test accuracy, maintained robust performance under 10% salt-and-pepper noise, and achieved cross-dataset generalization exceeding 80% in certain conditions. Comparisons with state-of-the-art (SOTA) models like vision transformers (ViTs) and convolutional neural networks (CNNs) demonstrate the HCdM’s robustness and efficiency. Additionally, in contrast to previous artificial visual systems (AVSs), our findings suggest that lateral geniculate nucleus (LGN) structures, though present in biological vision, may not be essential for motion direction detection. This insight provides a new direction for bio-inspired computational models. Future research will focus on hybridizing the HCdM with SOTA models that perform well on complex visual scenes to enhance its adaptability. Full article

The advancement of autonomous vehicles has shifted from modular pipeline architectures to end-to-end frameworks, enabling direct learning of control policies from sensory inputs. While frame-based RGB cameras are commonly utilized, they face challenges in dynamic environments, such as motion blur and varying illumination. Alternatively, event-based cameras, with their high temporal resolution and wide dynamic range, offer a promising solution. However, existing end-to-end models for event camera inputs are primarily constructed using traditional convolutional networks and time-sequence models (e.g., Recurrent Neural Networks, RNNs), which suffer from large parameter counts and excessive redundant computations. To address this gap, we propose LiS-Net, a novel framework that incorporates brain-inspired neural networks to construct the overall architecture, applying it to the task of end-to-end steering prediction. The core of LiS-Net is a liquid neural network, which is designed to simulate the behavior of C. elegans neurons for modeling purposes. By leveraging the strengths of event cameras and brain-inspired computation, LiS-Net achieves superior accuracy, smoothness, and efficiency. Specifically, LiS-Net outperforms existing models with the lowest RMSE and MAE, indicating better accuracy, while also maintaining the fewest number of neurons and achieving competitive FLOPs results, showcasing its computational efficiency. Experiments on the simulated EventScape dataset demonstrate its robustness, while validation on our self-collected dataset showcases its generalization capability. We also release the collected dataset comprising synchronized event cameras, RGB cameras, and GPS and CAN data. LiS-Net lays the foundation for scalable and efficient autonomous driving solutions by integrating bio-inspired sensors with brain-inspired computation. Full article

Deep Neural Networks (DNNs) have been widely used to solve complex problems in natural language processing, image classification, and autonomous systems. The strength of DNNs is derived from their ability to model complex functions and to improve detection engines through deeper architecture. Despite the strengths of DNN engines, they present several crucial challenges, such as the number of hidden layers, the learning rate, and the neuron weight. These parameters are considered to play a crucial role in the ability of DNNs to detect anomalies. Optimizing these parameters could improve the detection engine and expand the utilization of DNNs for various areas of application. Bio-inspired optimization algorithms, especially Particle Swarm Intelligence (PSO) and the Gray Wolf Optimizer (GWO), have been widely used to optimize complex tasks because of their ability to explore the search space and their fast convergence. Despite the significant successes of PSO and GWO, there remains a gap in the literature regarding their hybridization and application in Intrusion Detection Systems (IDSs), such as Sunburst attack detection, especially using DNN. Therefore, in this paper, we introduce a hybrid detection model that investigates the ability to integrate PSO and GWO so as to improve the DNN architecture to detect the Sunburst attack. The PSO algorithm was used to optimize the learning rate and the number of hidden layers, while the GWO algorithm was used to optimize the neuron weight. The hybrid model was tested and evaluated based on open-source Sunburst attacks. The results demonstrate the effectiveness and robustness of the suggested hybrid DNN model. Furthermore, an extensive analysis was conducted by evaluating the suggested hybrid PSO–GWO along with other hybrid optimization techniques, namely Genetic Algorithm (GA), Differential Evolution (DE), and Ant Colony Optimization (ACO). The results demonstrate that the suggested hybrid model outperformed other optimization techniques in terms of accuracy, precision, recall, and F1-score. Full article

Background: Brain-inspired models are commonly employed for artificial intelligence. However, the complex environment can hinder the performance of electronic equipment. Therefore, enhancing the injury resistance of brain-inspired models is a crucial issue. Human brains have self-adaptive abilities under injury, so drawing on the advantages of the human brain to construct a brain-inspired model is intended to enhance its injury resistance. But current brain-inspired models still lack bio-plausibility, meaning they do not sufficiently draw on real neural systems’ structure or function. Methods: To address this challenge, this paper proposes the complex spiking neural network (Com-SNN) as a brain-inspired model, in which the topology is inspired by the topological characteristics of biological functional brain networks, the nodes are Izhikevich neuron models, and the edges are synaptic plasticity models with time delay co-regulated by excitatory synapses and inhibitory synapses. To evaluate the injury resistance of the Com-SNN, two injury-resistance metrics are investigated and compared with SNNs with alternative topologies under the stochastic removal of neuron models to simulate the consequence of stochastic attacks. In addition, the injury-resistance mechanism of brain-inspired models remains unclear, and revealing the mechanism is crucial for understanding the development of SNNs with injury resistance. To address this challenge, this paper analyzes the synaptic plasticity dynamic regulation and dynamic topological characteristics of the Com-SNN under stochastic attacks. Results: The experimental results indicate that the injury resistance of the Com-SNN is superior to that of other SNNs, demonstrating that our results can help improve the injury resistance of SNNs. Conclusions: Our results imply that synaptic plasticity is an intrinsic element impacting injury resistance, and that network topology is another element that impacts injury resistance. Full article

(1) Background: At present, the bio-inspired visual neural models have made significant achievements in detecting the motion direction of the translating object. Variable contrast in the figure-ground and environmental noise interference, however, have a strong influence on the existing model. The responses of the lobula plate tangential cell (LPTC) neurons of Drosophila are robust and stable in the face of variable contrast in the figure-ground and environmental noise interference, which provides an excellent paradigm for addressing these challenges. (2) Methods: To resolve these challenges, we propose a bio-inspired visual neural model, which consists of four stages. Firstly, the photoreceptors (R1–R6) are utilized to perceive the change in luminance. Secondly, the change in luminance is divided into parallel ON and OFF pathways based on the lamina monopolar cell (LMC), and the spatial denoising and the spatio-temporal lateral inhibition (LI) mechanisms can suppress environmental noise and improve motion boundaries, respectively. Thirdly, the non-linear instantaneous feedback mechanism in divisive contrast normalization is adopted to reduce local contrast sensitivity; further, the parallel ON and OFF contrast pathways are activated. Finally, the parallel motion and contrast pathways converge on the LPTC in the lobula complex. (3) Results: By comparing numerous experimental simulations with state-of-the-art (SotA) bio-inspired models, we can draw four conclusions. Firstly, the effectiveness of the contrast neural computation and the spatial denoising mechanism is verified by the ablation study. Secondly, this model can robustly detect the motion direction of the translating object against variable contrast in the figure-ground and environmental noise interference. Specifically, the average detection success rate of the proposed bio-inspired model under the pure and real-world complex noise datasets was increased by 5.38% and 5.30%. Thirdly, this model can effectively reduce the fluctuation in this model response against variable contrast in the figure-ground and environmental noise interference, which shows the stability of this model; specifically, the average inter-quartile range of the coefficient of variation in the proposed bio-inspired model under the pure and real-world complex noise datasets was reduced by 38.77% and 47.84%, respectively. The average decline ratio of the sum of the coefficient of variation in the proposed bio-inspired model under the pure and real-world complex noise datasets was 57.03% and 67.47%, respectively. Finally, the robustness and stability of this model are further verified by comparing other early visual pre-processing mechanisms and engineering denoising methods. (4) Conclusions: This model can robustly and steadily detect the motion direction of the translating object under variable contrast in the figure-ground and environmental noise interference. Full article

Path planning for multi-robot systems in complex dynamic environments is a key issue in autonomous robotics research. In response to the challenges posed by such environments, this paper proposes a dual-layer symmetric path planning algorithm that integrates an improved Glasius bio-inspired neural network (GBNN) and an enhanced dynamic window approach (DWA). This algorithm enables real-time obstacle avoidance for multi-robots in dynamic environments while effectively addressing robot-to-robot conflict issues. First, to address the low global optimization capability of the GBNN algorithm in the first layer, a signal waveform propagation model for single-neuron signals is established, enhancing the global optimization ability of the algorithm. Additionally, a path optimization function is developed to remove redundant points along the path, improving its efficiency. In the second layer, based on the global path, a reward function is introduced into the DWA. The Score function within the DWA algorithm is also modified to enable symmetric path adjustments, effectively reducing detour paths and minimizing the probability of deviation from the planned trajectory while ensuring real-time obstacle avoidance under the condition of maintaining the global path’s optimality. Next, to address conflicts arising from multi-robot encounters, a dynamic priority method based on distance is proposed. Finally, through multi-dimensional comparative experiments, the superiority of the proposed method is validated. Experimental results show that, compared with other algorithms, the improved neural network-DWA algorithm significantly reduces path length and the number of turns. This research contributes to enhancing the efficiency, adaptability, and safety of multi-robot systems. Full article

By analyzing reconstructed three-dimensional images of retinal bipolar neurons, we show that their dendritic arbors weave through space in a manner that generates fractal-like behavior quantified by an ‘effective’ fractal dimension. Examining this fractal weave along with traditional morphological parameters reveals a dependence of arbor fractal dimension on the summation of the lengths of the arbor’s dendrites. We discuss the implications of this behavior for healthy neurons and also for the morphological deterioration of unhealthy neurons in response to diseases. Full article

Animals utilize their well-evolved dynamic vision systems to perceive and evade collision threats. Driven by biological research, bio-inspired models based on lobula giant movement detectors (LGMDs) address certain gaps in constructing artificial collision-detecting vision systems with robust selectivity, offering reliable, low-cost, and miniaturized collision sensors across various scenes. Recent progress in neuroscience has revealed the energetic advantages of dendritic arrangements presynaptic to the LGMDs, which receive contrast polarity-specific signals on separate dendritic fields. Specifically, feed-forward inhibitory inputs arise from parallel ON/OFF pathways interacting with excitation. However, none of the previous research has investigated the evolution of a computational LGMD model with feed-forward inhibition (FFI) separated by opposite polarity. This study fills this vacancy by presenting an optimized neuronal model where FFI is divided into ON/OFF channels, each with distinct synaptic connections. To align with the energy efficiency of biological systems, we introduce an activation function associated with neural computation of FFI and interactions between local excitation and lateral inhibition within ON/OFF channels, ignoring non-active signal processing. This approach significantly improves the time efficiency of the LGMD model, focusing only on substantial luminance changes in image streams. The proposed neuronal model not only accelerates visual processing in relatively stationary scenes but also maintains robust selectivity to ON/OFF-contrast looming stimuli. Additionally, it can suppress translational motion to a moderate extent. Comparative testing with state-of-the-art based on ON/OFF channels was conducted systematically using a range of visual stimuli, including indoor structured and complex outdoor scenes. The results demonstrated significant time savings in silico while retaining original collision selectivity. Furthermore, the optimized model was implemented in the embedded vision system of a micro-mobile robot, achieving the highest success ratio of collision avoidance at 97.51% while nearly halving the processing time compared with previous models. This highlights a robust and parsimonious collision-sensing mode that effectively addresses real-world challenges. Full article

This study compares bio-inspired optimization algorithms for enhancing an ANN-based Maximum Power Point Tracking (MPPT) forecast system under partial shading conditions in photovoltaic systems. Four algorithms—grey wolf optimizer (GWO), particle swarm optimization (PSO), squirrel search algorithm (SSA), and cuckoo search (CS)—were evaluated, with the dataset augmented by perturbations to simulate shading. The standard ANN performed poorly, with 64 neurons in Layer 1 and 32 in Layer 2 (MSE of 159.9437, MAE of 8.0781). Among the optimized approaches, GWO, with 66 neurons in Layer 1 and 100 in Layer 2, achieved the best prediction accuracy (MSE of 11.9487, MAE of 2.4552) and was computationally efficient (execution time of 1198.99 s). PSO, using 98 neurons in Layer 1 and 100 in Layer 2, minimized MAE (2.1679) but had a slightly longer execution time (1417.80 s). SSA, with the same neuron count as GWO, also performed well (MSE 12.1500, MAE 2.7003) and was the fastest (987.45 s). CS, with 84 neurons in Layer 1 and 74 in Layer 2, was less reliable (MSE 33.7767, MAE 3.8547) and slower (1904.01 s). GWO proved to be the best overall, balancing accuracy and speed. Future real-world applications of this methodology include improving energy efficiency in solar farms under variable weather conditions and optimizing the performance of residential solar panels to reduce energy costs. Further optimization developments could address more complex and larger-scale datasets in real-time, such as integrating renewable energy sources into smart grid systems for better energy distribution. Full article

This study examines a new approach to hybrid neuromorphic devices by studying the impact of omeprazole–proteinoid complexes on Izhikevich neuron models. We investigate the influence of these metabolic structures on five specific patterns of neuronal firing: accommodation, chattering, triggered spiking, phasic spiking, and tonic spiking. By combining omeprazole, a proton pump inhibitor, with proteinoids, we create a unique substrate that interfaces with neuromorphic models. The Izhikevich neuron model is used because it is computationally efficient and can accurately simulate the various behaviours of cortical neurons. The results of our simulations show that omeprazole–proteinoid complexes have the ability to affect neuronal dynamics in different ways. This suggests that they could be used as adjustable components in bio-inspired computer systems. We noticed a notable alteration in the frequency of spikes, patterns of bursts, and rates of adaptation, especially in chattering and triggered spiking behaviours. The findings indicate that omeprazole–proteinoid complexes have the potential to serve as adaptable elements in neuromorphic systems, presenting novel opportunities for information processing and computation that have origins in neurobiological principles. This study makes a valuable contribution to the expanding field of biochemical neuromorphic devices and establishes a basis for the development of hybrid bio-synthetic computational systems. Full article

In recent research, dendritic neuron-based models have shown promise in effectively learning and recognizing object motion direction within binary images. Leveraging the dendritic neuron structure and On–Off Response mechanism within the primary cortex, this approach has notably reduced learning time and costs compared to traditional neural networks. This paper advances the existing model by integrating bio-inspired components into a learnable dendritic neuron-based artificial visual system (AVS), specifically incorporating mechanisms from horizontal and bipolar cells. This enhancement enables the model to proficiently identify object motion directions in grayscale images, aligning its threshold with human-like perception. The enhanced model demonstrates superior efficiency in motion direction recognition, requiring less data (90% less than other deep models) and less time for training. Experimental findings highlight the model’s remarkable robustness, indicating significant potential for real-world applications. The integration of bio-inspired features not only enhances performance but also opens avenues for further exploration in neural network research. Notably, the application of this model to realistic object recognition yields convincing accuracy at nearly 100%, underscoring its practical utility. Full article