Improving Multispike Learning With Plastic Synaptic Delays

Delayed knowledge transfer: Cross-modal knowledge transfer from delayed stimulus to EEG for continuous attention detection based on spike-represented EEG signals

Decoding visual and auditory stimuli from brain activities, such as electroencephalography (EEG), offers promising advancements for enhancing machine-to-human interaction. However, effectively representing EEG signals remains a significant challenge. In this paper, we introduce a novel Delayed Knowledge Transfer (DKT) framework that employs spiking neurons for attention detection, using our experimental EEG dataset. This framework extracts patterns from audiovisual stimuli to model brain responses in EEG signals, while accounting for inherent response delays. By aligning audiovisual features with EEG signals through a shared embedding space, our approach improves the performance of brain-computer interface (BCI) systems. We also present WithMeAttention, a multimodal dataset designed to facilitate research in continuously distinguishing between target and distractor responses. Our methodology demonstrates a 3% improvement in accuracy on the WithMeAttention dataset compared to a baseline model that decodes EEG signals from scratch. This significant performance increase highlights the effectiveness of our approach Comprehensive analysis across four distinct conditions shows that rhythmic enhancement of visual information can optimize multi-sensory information processing. Notably, the two conditions featuring rhythmic target presentation - with and without accompanying beeps - achieved significantly superior performance compared to other scenarios. Furthermore, the delay distribution observed under different conditions indicates that our delay layer effectively emulates the neural processing delays in response to stimuli.

Complex Spiking Neural Network Evaluated by Injury Resistance Under Stochastic Attacks

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.

Fault-Tolerant Attitude Tracking Control Driven by Spiking NNs for Unmanned Aerial Vehicles

In this article, we proposed a novel fault-tolerant control scheme for quadrotor unmanned aerial vehicles (UAVs) based on spiking neural networks (SNNs), which leverages the inherent features of neural network computing to significantly enhance the reliability and robustness of UAV flight control. Traditional control methods are known to be inadequate in dealing with complex and real-time sensor data, which results in poor performance and reduced robustness in fault-tolerant control. In contrast, the temporal processing, parallelism, and nonlinear capacity of SNNs enable the fault-tolerant control scheme to process vast amounts of sensory data with the ability to accurately identify and respond to faults. Furthermore, SNNs can learn and adjust to new environments and fault conditions, providing effective and adaptive flight control. The proposed SNN-based fault-tolerant control scheme demonstrates significant improvements in control accuracy and robustness compared with conventional methods, indicating its potential applicability and suitability for a range of UAV flight control scenarios.

Direct learning-based deep spiking neural networks: a review

The spiking neural network (SNN), as a promising brain-inspired computational model with binary spike information transmission mechanism, rich spatially-temporal dynamics, and event-driven characteristics, has received extensive attention. However, its intricately discontinuous spike mechanism brings difficulty to the optimization of the deep SNN. Since the surrogate gradient method can greatly mitigate the optimization difficulty and shows great potential in directly training deep SNNs, a variety of direct learning-based deep SNN works have been proposed and achieved satisfying progress in recent years. In this paper, we present a comprehensive survey of these direct learning-based deep SNN works, mainly categorized into accuracy improvement methods, efficiency improvement methods, and temporal dynamics utilization methods. In addition, we also divide these categorizations into finer granularities further to better organize and introduce them. Finally, the challenges and trends that may be faced in future research are prospected.