Recently, brain-inspired spiking neuron networks (SNNs) have attracted widespread research interest because of their event-driven and energy-efficient characteristics. Still, it is difficult to efficiently train deep SNNs due to the nondifferentiability of its activation function, which disables the typically used gradient descent approaches for traditional artificial neural networks (ANNs). Although the adoption of surrogate gradient (SG) formally allows for the back-propagation of losses, the discrete spiking mechanism actually differentiates the loss landscape of SNNs from that of ANNs, failing the surrogate gradient methods to achieve comparable accuracy as for ANNs. In this paper, we first analyze why the current direct training approach with surrogate gradient results in SNNs with poor generalizability. Then we introduce the temporal efficient training (TET) approach to compensate for the loss of momentum in the gradient descent with SG so that the training process can converge into flatter minima with better generalizability. Meanwhile, we demonstrate that TET improves the temporal scalability of SNN and induces a temporal inheritable training for acceleration. Our method consistently outperforms the SOTA on all reported mainstream datasets, including CIFAR-10/100 and ImageNet. Remarkably on DVS-CIFAR10, we obtained 83% top-1 accuracy, over 10% improvement compared to existing state of the art. Codes are available at https://github.com/Gus-Lab/temporal_ efficient_training.

Spiking neural networks (SNNs) are biology-inspired artificial neural networks (ANNs) that comprise of spiking neurons to process asynchronous discrete signals. While more efficient in power consumption and inference speed on the neuromorphic hardware, SNNs are usually difficult to train directly from scratch with spikes due to the discreteness. As an alternative, many efforts have been devoted to converting conventional ANNs into SNNs by copying the weights from ANNs and adjusting the spiking threshold potential of neurons in SNNs. Researchers have designed new SNN architectures and conversion algorithms to diminish the conversion error. However, an effective conversion should address the difference between the SNN and ANN architectures with an efficient approximation of the loss function, which is missing in the field. In this work, we analyze the conversion error by recursive reduction to layer-wise summation and propose a novel strategic pipeline that transfers the weights to the target SNN by combining threshold balance and soft-reset mechanisms. This pipeline enables almost no accuracy loss between the converted SNNs and conventional ANNs with only ∼ 1/10 of the typical SNN simulation time. Our method is promising to get implanted onto embedded platforms with better support of SNNs with limited energy and memory. Codes are available at https://github.com/Jackn0/snn optimal conversion pipeline.

No abstract

The brain’s functional connectivity fluctuates over time instead of remaining steady in a stationary mode even during the resting state. This fluctuation establishes the dynamical functional connectivity that transitions in a non-random order between multiple modes. Yet it remains unexplored how the transition facilitates the entire brain network as a dynamical system and what utility this mechanism for dynamic reconfiguration can bring over the widely used graph theoretical measurements. To address these questions, we propose to conduct an energetic analysis of functional brain networks using resting-state fMRI and behavioral measurements from the Human Connectome Project. Through comparing the state transition energy under distinct adjacent matrices, we justify that dynamic functional connectivity leads to 60% less energy cost to support the resting state dynamics than static connectivity when driving the transition through default mode network. Moreover, we demonstrate that combining graph theoretical measurements and our energy-based control measurements as the feature vector can provide complementary prediction power for the behavioral scores (Combination vs. Control: t = 9.41, p = 1.64e−13; Combination vs. Graph: t = 4.92, p = 3.81e−6). Our approach integrates statistical inference and dynamical system inspection towards understanding brain networks.

Background and Hypothesis Disrupted control of brain state transitions may contribute to the diverse dysfunctions of cognition, emotion, and behavior that are fundamental to schizophrenia. Control theory provides the rationale for evaluating brain state transitions from a controllability perspective, which may help reveal the brain mechanism for clinical features such as cognitive control deficits associated with schizophrenia. We hypothesized that brain controllability would be altered in patients with schizophrenia, and that controllability of brain networks would be related to clinical symptomatology. Study Design Controllability measurements of functional brain networks, including average controllability and modal controllability, were calculated and compared between 125 first-episode never-treated patients with schizophrenia and 133 healthy controls (HCs). Associations between controllability metrics and clinical symptoms were evaluated using sparse canonical correlation analysis. Study Results Compared to HCs, patients showed significantly increased average controllability (PFDR = .023) and decreased modal controllability (PFDR = .023) in dorsal anterior cingulate cortex (dACC). General psychopathology symptoms and positive symptoms were positively correlated with average controllability in regions of default mode network and negatively associated with average controllability in regions of sensorimotor, dorsal attention, and frontoparietal networks. Conclusions Our findings suggest that altered controllability of functional activity in dACC may play a critical role in the pathophysiology of schizophrenia, consistent with the importance of this region in cognitive and brain state control operations. The demonstration of associations of functional controllability with psychosis symptoms suggests that the identified alterations in average controllability of brain function may contribute to the severity of acute psychotic illness in schizophrenia.