SNNs can be generalized to 3D recognition.

Spiking neural networks (SNNs) have undergone continuous development and extensive research over the decades to improve biological plausibility while optimizing energy efficiency. However, traditional deep SNN training methods have some limitations, and they rely on strategies such as pre-training and fine-tuning, indirect encoding and reconstruction, and approximate gradients. These strategies lack complete training models and lack biocompatibility. To overcome these limitations, we propose a novel learning method named Deep Spiking Neural Networks with Joint Excitatory Inhibition Loop Iterative Learning (EICIL). Inspired by biological neuron signal transmission, this method integrates excitatory and inhibitory behaviors in neurons, organically combining these two behavioral modes into one framework. EICIL significantly improves the biomimicry and adaptability of spiking neuron models and expands the representation space of spiking neurons. Extensive experiments based on EICIL and traditional learning methods show that EICIL outperforms traditional methods on various datasets such as CIFAR10 and CIFAR100, demonstrating the key role of learning methods that integrate both behaviors during training.

Spiking Neural Networks (SNNs) have been studied over decades to incorporate their biological plausibility and leverage their promising energy efficiency.

Spiking Neural Networks (SNNs) have shown substantial promise in processing spatio-temporal data, mimicking biological neuronal mechanisms, and saving computational power. However, most SNNs use fixed model regardless of their locations in the network. This limits SNNs' capability of transmitting precise information in the network, which becomes worse for deeper SNNs. Some researchers try to use specified parametric models in different network layers or regions, but most still use preset or suboptimal parameters. Inspired by the neuroscience observation that different neuronal mechanisms exist in disparate brain regions, we propose a new spiking neuronal mechanism, named learnable thresholding, to address this issue.

Spiking neural networks (SNNs), inspired by biological processes, use spike signals for inter-layer communication, presenting an energy-efficient alternative to traditional neural networks. To realize the theoretical advantages of SNNs in energy efficiency, it is essential to deploy them onto neuromorphic chips. On clock-driven synchronous chips, employing shorter time steps can enhance energy efficiency but reduce SNN performance. Compared to the clock-driven synchronous chip, the event-driven asynchronous chip achieves much lower energy consumption but only supports some specific network operations. Recently, a series of SNN projects have achieved tremendous success, significantly improving the SNN's performance. However, event-driven asynchronous chips do not support some of the proposed structures, making it impossible to integrate these SNNs into asynchronous hardware. In response to these problems, we propose the Spiking Token Mixer (STMixer) architecture, which consists exclusively of operations supported by asynchronous scenarios, including convolutional, fully connected layers and residual paths. Our series of experiments also demonstrates that STMixer achieves performance on par with spiking transformers in synchronous scenarios with very low timesteps. This indicates its ability to achieve the same level of performance with lower power consumption in synchronous scenarios.

Deep neural networks (DNNs) have showcased their remarkable precision in approximating smooth functions. However, they suffer from the {\it spectral bias}, wherein DNNs typically exhibit a tendency to prioritize the learning of lower-frequency components of a function, struggling to effectively capture its high-frequency features. This paper is to address this issue. Notice that a function having only low frequency components may be well-represented by a shallow neural network (SNN), a network having only a few layers. By observing that composition of low frequency functions can effectively approximate a high-frequency function, we propose to learn a function containing high-frequency components by composing several SNNs, each of which learns certain low-frequency information from the given data.