Exploring spiking neural networks: a comprehensive analysis of mathematical models and applications.

This article presents a comprehensive analysis of spiking neural networks (SNNs) and their mathematical models for simulating the behavior of neurons through the generation of spikes. The study explores various models, including LIF and NLIF, for constructing SNNs and investigates their potential applications in different domains. However, implementation poses several challenges, including identifying the most appropriate model for classification tasks that demand high accuracy and low-performance loss. To address this issue, this research study compares the performance, behavior, and spike generation of multiple SNN models using consistent inputs and neurons. The findings of the study provide valuable insights into the benefits and challenges of SNNs and their models, emphasizing the significance of comparing multiple models to identify the most effective one. Moreover, the study quantifies the number of spiking operations required by each model to process the same inputs and produce equivalent outputs, enabling a thorough assessment of computational efficiency. The findings provide valuable insights into the benefits and limitations of SNNs and their models. The research underscores the significance of comparing different models to make informed decisions in practical applications. Additionally, the results reveal essential variations in biological plausibility and computational efficiency among the models, further emphasizing the importance of selecting the most suitable model for a given task. Overall, this study contributes to a deeper understanding of SNNs and offers practical guidelines for using their potential in real-world scenarios.

Evaluation of Spiking Neural Nets-Based Image Classification Using the Runtime Simulator RAVSim.

Spiking Neural Networks (SNNs) help achieve brain-like efficiency and functionality by building neurons and synapses that mimic the human brain's transmission of electrical signals. However, optimal SNN implementation requires a precise balance of parametric values. To design such ubiquitous neural networks, a graphical tool for visualizing, analyzing, and explaining the internal behavior of spikes is crucial. Although some popular SNN simulators are available, these tools do not allow users to interact with the neural network during simulation. To this end, we have introduced the first runtime interactive simulator, called Runtime Analyzing and Visualization Simulator (RAVSim),a developed to analyze and dynamically visualize the behavior of SNNs, allowing end-users to interact, observe output concentration reactions, and make changes directly during the simulation. In this paper, we present RAVSim with the current implementation of runtime interaction using the LIF neural model with different connectivity schemes, an image classification model using SNNs, and a dataset creation feature. Our main objective is to primarily investigate binary classification using SNNs with RGB images. We created a feed-forward network using the LIF neural model for an image classification algorithm and evaluated it by using RAVSim. The algorithm classifies faces with and without masks, achieving an accuracy of 91.8% using 1000 neurons in a hidden layer, 0.0758 MSE, and an execution time of ∼10[Formula: see text]min on the CPU. The experimental results show that using RAVSim not only increases network design speed but also accelerates user learning capability.

µRT: A lightweight real-time middleware with integrated validation of timing constraints.

Middlewares are standard tools for modern software development in many areas, especially in robotics. Although such have become common for high-level applications, there is little support for real-time systems and low-level control. Therefore, µRT provides a lightweight solution for resource-constrained embedded systems, such as microcontrollers. It features publish-subscribe communication and remote procedure calls (RPCs) and can validate timing constraints at runtime. In contrast to other middlewares, µRT does not rely on specific transports for communication but can be used with any technology. Empirical results prove the small memory footprint, consistent temporal behavior, and predominantly linear scaling. The usability of µRT was found to be competitive with state-of-the-art solutions by means of a study.

Benchmarking Neuromorphic Hardware and Its Energy Expenditure.

We propose and discuss a platform overarching benchmark suite for neuromorphic hardware. This suite covers benchmarks from low-level characterization to high-level application evaluation using benchmark specific metrics. With this rather broad approach we are able to compare various hardware systems including mixed-signal and fully digital neuromorphic architectures. Selected benchmarks are discussed and results for several target platforms are presented revealing characteristic differences between the various systems. Furthermore, a proposed energy model allows to combine benchmark performance metrics with energy efficiency. This model enables the prediction of the energy expenditure of a network on a target system without actually having access to it. To quantify the efficiency gap between neuromorphics and the biological paragon of the human brain, the energy model is used to estimate the energy required for a full brain simulation. This reveals that current neuromorphic systems are at least four orders of magnitude less efficient. It is argued, that even with a modern fabrication process, two to three orders of magnitude are remaining. Finally, for selected benchmarks the performance and efficiency of the neuromorphic solution is compared to standard approaches.

Acceleration of the SPADE Method Using a Custom-Tailored FP-Growth Implementation.

The SPADE (spatio-temporal Spike PAttern Detection and Evaluation) method was developed to find reoccurring spatio-temporal patterns in neuronal spike activity (parallel spike trains). However, depending on the number of spike trains and the length of recording, this method can exhibit long runtimes. Based on a realistic benchmark data set, we identified that the combination of pattern mining (using the FP-Growth algorithm) and the result filtering account for 85-90% of the method's total runtime. Therefore, in this paper, we propose a customized FP-Growth implementation tailored to the requirements of SPADE, which significantly accelerates pattern mining and result filtering. Our version allows for parallel and distributed execution, and due to the improvements made, an execution on heterogeneous and low-power embedded devices is now also possible. The implementation has been evaluated using a traditional workstation based on an Intel Broadwell Xeon E5-1650 v4 as a baseline. Furthermore, the heterogeneous microserver platform RECS|Box has been used for evaluating the implementation on two HiSilicon Hi1616 (Kunpeng 916), an Intel Coffee Lake-ER Xeon E-2276ME, an Intel Broadwell Xeon D-D1577, and three NVIDIA Tegra devices (Jetson AGX Xavier, Jetson Xavier NX, and Jetson TX2). Depending on the platform, our implementation is between 27 and 200 times faster than the original implementation. At the same time, the energy consumption was reduced by up to two orders of magnitude.

Resource-efficient bio-inspired visual processing on the hexapod walking robot HECTOR.

Emulating the highly resource-efficient processing of visual motion information in the brain of flying insects, a bio-inspired controller for collision avoidance and navigation was implemented on a novel, integrated System-on-Chip-based hardware module. The hardware module is used to control visually-guided navigation behavior of the stick insect-like hexapod robot HECTOR. By leveraging highly parallelized bio-inspired algorithms to extract nearness information from visual motion in dynamically reconfigurable logic, HECTOR is able to navigate to predefined goal positions without colliding with obstacles. The system drastically outperforms CPU- and graphics card-based implementations in terms of speed and resource efficiency, making it suitable to be also placed on fast moving robots, such as flying drones.

Numerical and Experimental Evaluation of Error Estimation for Two-Way Ranging Methods.

The Two-Way Ranging (TWR) method is commonly used for measuring the distance between two wireless transceiver nodes, especially when clock synchronization between the two nodes is not available. For modeling the time-of-flight (TOF) error between two wireless transceiver nodes in TWR, the existing error model, described in the IEEE 802.15.4-2011 standard, is solely based on clock drift. However, it is inadequate for in-depth comparative analysis between different TWR methods. In this paper, we propose a novel TOF Error Estimation Model (TEEM) for TWR methods. Using the proposed model, we evaluate the comparative analysis between different TWR methods. The analytical results were validated with both numerical simulation and experimental results. Moreover, we demonstrate the pitfalls of the symmetric double-sided TWR (SDS-TWR) method, which is the most highlighted TWR method in the literature because of its highly accurate performance on clock-drift error reduction when reply times are symmetric. We argue that alternative double-sided TWR (AltDS-TWR) outperforms SDS-TWR. The argument was verified with both numerical simulation and experimental evaluation results.

Technical feasibility study for production of tailored multielectrode arrays and patterning of arranged neuronal networks.

In this manuscript, we first reveal a simple ultra violet laser lithographic method to design and produce plain tailored multielectrode arrays. Secondly, we use the same lithographic setup for surface patterning to enable controlled attachment of primary neuronal cells and help neurite guidance. For multielectrode array production, we used flat borosilicate glass directly structured with the laser lithography system. The multi layered electrode system consists of a layer of titanium coated with a layer of di-titanium nitride. Finally, these electrodes are covered with silicon nitride for insulation. The quality of the custom made multielectrode arrays was investigated by light microscopy, electron microscopy and X-ray diffraction. The performance was verified by the detection of action potentials of primary neurons. The electrical noise of the custom-made MEA was equal to commercially available multielectrode arrays. Additionally, we demonstrated that structured coating with poly lysine, obtained with the aid of the same lithographic system, could be used to attach and guide neurons to designed structures. The process of neuron attachment and neurite guidance was investigated by light microscopy and charged particle microscopy. Importantly, the utilization of the same lithographic system for MEA fabrication and poly lysine structuring will make it easy to align the architecture of the neuronal network to the arrangement of the MEA electrode.. In future studies, this will lead to multielectrode arrays, which are able to specifically attach neuronal cell bodies to their chemically defined electrodes and guide their neurites, gaining a controlled connectivity in the neuronal network. This type of multielectrode array would be able to precisely assign a signal to a certain neuron resulting in an efficient way for analyzing the maturation of the neuronal connectivity in small neuronal networks.

Multi-Modal Detection and Mapping of Static and Dynamic Obstacles in Agriculture for Process Evaluation.

Today, agricultural vehicles are available that can automatically perform tasks such as weed detection and spraying, mowing, and sowing while being steered automatically. However, for such systems to be fully autonomous and self-driven, not only their specific agricultural tasks must be automated. An accurate and robust perception system automatically detecting and avoiding all obstacles must also be realized to ensure safety of humans, animals, and other surroundings. In this paper, we present a multi-modal obstacle and environment detection and recognition approach for process evaluation in agricultural fields. The proposed pipeline detects and maps static and dynamic obstacles globally, while providing process-relevant information along the traversed trajectory. Detection algorithms are introduced for a variety of sensor technologies, including range sensors (lidar and radar) and cameras (stereo and thermal). Detection information is mapped globally into semantical occupancy grid maps and fused across all sensors with late fusion, resulting in accurate traversability assessment and semantical mapping of process-relevant categories (e.g., crop, ground, and obstacles). Finally, a decoding step uses a Hidden Markov model to extract relevant process-specific parameters along the trajectory of the vehicle, thus informing a potential control system of unexpected structures in the planned path. The method is evaluated on a public dataset for multi-modal obstacle detection in agricultural fields. Results show that a combination of multiple sensor modalities increases detection performance and that different fusion strategies must be applied between algorithms detecting similar and dissimilar classes.

Binary Associative Memories as a Benchmark for Spiking Neuromorphic Hardware.

Large-scale neuromorphic hardware platforms, specialized computer systems for energy efficient simulation of spiking neural networks, are being developed around the world, for example as part of the European Human Brain Project (HBP). Due to conceptual differences, a universal performance analysis of these systems in terms of runtime, accuracy and energy efficiency is non-trivial, yet indispensable for further hard- and software development. In this paper we describe a scalable benchmark based on a spiking neural network implementation of the binary neural associative memory. We treat neuromorphic hardware and software simulators as black-boxes and execute exactly the same network description across all devices. Experiments on the HBP platforms under varying configurations of the associative memory show that the presented method allows to test the quality of the neuron model implementation, and to explain significant deviations from the expected reference output.

How little do we actually know? On the size of gene regulatory networks.

The National Center for Biotechnology Information (NCBI) recently announced the availability of whole genome sequences for more than 1,000 species. And the number of sequenced individual organisms is growing. Ongoing improvement of DNA sequencing technology will further contribute to this, enabling large-scale evolution and population genetics studies. However, the availability of sequence information is only the first step in understanding how cells survive, reproduce, and adjust their behavior. The genetic control behind organized development and adaptation of complex organisms still remains widely undetermined. One major molecular control mechanism is transcriptional gene regulation. The direct juxtaposition of the total number of sequenced species to the handful of model organisms with known regulations is surprising. Here, we investigate how little we even know about these model organisms. We aim to predict the sizes of the whole-organism regulatory networks of seven species. In particular, we provide statistical lower bounds for the expected number of regulations. For Escherichia coli we estimate at most 37 percent of the expected gene regulatory interactions to be already discovered, 24 percent for Bacillus subtilis, and <3% human, respectively. We conclude that even for our best researched model organisms we still lack substantial understanding of fundamental molecular control mechanisms, at least on a large scale.

Learning a predictive model for growth inhibition from the NCI DTP human tumor cell line screening data: does gene expression make a difference?

We address the problem of learning a predictive model for growth inhibition from the NCI DTP human tumor cell line screening data. Extending the classical Quantitative Structure Activity Relationship paradigm, we investigate whether including gene expression data leads to a statistically significant improvement of prediction quality. Our analysis shows that the straightforward approach of including individual gene expression as features does not necessarily improve, but on the contrary, may degrade performance significantly. When gene expression information is aggregated, for instance by features representing the correlation with reference cell lines, performance can be improved significantly. Further improvements may be expected if the learning task is structured by grouping features and instances.

Analyzing microarray data using quantitative association rules.

MOTIVATION: We tackle the problem of finding regularities in microarray data. Various data mining tools, such as clustering, classification, Bayesian networks and association rules, have been applied so far to gain insight into gene-expression data. Association rule mining techniques used so far work on discretizations of the data and cannot account for cumulative effects. In this paper, we investigate the use of quantitative association rules that can operate directly on numeric data and represent cumulative effects of variables. Technically speaking, this type of quantitative association rules based on half-spaces can find non-axis-parallel regularities. RESULTS: We performed a variety of experiments testing the utility of quantitative association rules for microarray data. First of all, the results should be statistically significant and robust against fluctuations in the data. Next, the approach should be scalable in the number of variables, which is important for such high-dimensional data. Finally, the rules should make sense biologically and be sufficiently different from rules found in regular association rule mining working with discretizations. In all of these dimensions, the proposed approach performed satisfactorily. Therefore, quantitative association rules based on half-spaces should be considered as a tool for the analysis of microarray gene-expression data. AVAILABILITY: The code is available from the authors on request.