DIET-SNN: A Low-Latency Spiking Neural Network with Direct Input Encoding &

DIET-SNN: A Low-Latency Spiking Neural Network with Direct Input Encoding & Leakage and Threshold Optimization

Bio-inspired spiking neural networks (SNNs), operating with asynchronous binary signals (or spikes) distributed over time, can potentially lead to greater computational efficiency on event-driven hardware. The state-of-the-art SNNs suffer from high inference latency, resulting from inefficient input encoding, and sub-optimal settings of the neuron parameters (firing threshold, and membrane leak).We propose DIET-SNN, a low latency deep spiking network that is trained with gradient descent to optimize the membrane leak and the firing threshold along with other network parameters (weights). The membrane leak and threshold for each layer of the SNN are optimized with end-to-end backpropagation to achieve competitive accuracy at reduced latency. The analog pixel values of an image are directly applied to the input layer of DIET-SNN without the need to convert to spike-train. The first convolutional layer is trained to convert inputs into spikes where leaky-integrate-and-fire (LIF) neurons integrate the weighted inputs and generate an output spike when the membrane potential crosses the trained firing threshold. The trained membrane leak controls the flow of input information and attenuates irrelevant inputs to increase the activation sparsity in the convolutional and linear layers of the network. The reduced latency combined with high activation sparsity provides large improvements in computational efficiency. We evaluate DIET-SNN on image classification tasks from CIFAR and ImageNet datasets on VGG and ResNet architectures. We achieve top-1 accuracy of 69% with 25 timesteps (inference latency) on the ImageNet dataset with 3.1x less compute energy than an equivalent standard ANN. Additionally, DIET-SNN performs 5-100x faster inference compared to other state-of-the-art SNN models.

DIET-SNN：具有直接输入编码和泄漏以及阈值优化的低延迟尖峰神经网络

具有生物启发性的尖峰神经网络（SNN），通过随时间分布的异步二进制信号（或尖峰）运行，可以潜在地提高事件驱动硬件的计算效率。由于输入编码效率低下以及神经元参数（发射阈值和膜泄漏）设置欠佳，导致最新的SNN遭受高推理延迟。.. 我们提出了DIET-SNN，这是一种低延迟的深脉冲网络，该网络经过梯度下降训练，可优化膜泄漏和触发阈值以及其他网络参数（权重）。通过端到端的反向传播优化了SNN每一层的膜泄漏和阈值，从而在减少延迟的情况下实现了竞争优势。图像的模拟像素值直接应用于DIET-SNN的输入层，而无需转换为峰值序列。训练第一卷积层将输入转换为尖峰，在其中泄漏积分和发射（LIF）神经元对加权输入进行积分，并在膜电位超过训练后的发射阈值时产生输出尖峰。受过训练的膜泄漏控制输入信息的流动并衰减不相关的输入，以增加网络的卷积和线性层中的激活稀疏性。减少的等待时间与高激活稀疏性相结合，大大提高了计算效率。我们评估来自VIF和ResNet架构上的CIFAR和ImageNet数据集的图像分类任务上的DIET-SNN。我们在ImageNet数据集上以25个时间步长（推理延迟）实现了69％的top-1准确性，其计算能力比等效的标准ANN少3.1倍。此外，与其他最新的SNN模型相比，DIET-SNN的推理速度提高了5-100倍。我们评估来自VIF和ResNet架构上的CIFAR和ImageNet数据集的图像分类任务上的DIET-SNN。我们在ImageNet数据集上以25个时间步长（推理延迟）实现了69％的top-1准确性，其计算能力比等效的标准ANN少3.1倍。此外，与其他最新的SNN模型相比，DIET-SNN的推理速度提高了5-100倍。我们评估来自VIF和ResNet架构上的CIFAR和ImageNet数据集的图像分类任务上的DIET-SNN。我们在ImageNet数据集上以25个时间步长（推理延迟）实现了69％的top-1准确性，其计算能力比等效的标准ANN少3.1倍。此外，与其他最新的SNN模型相比，DIET-SNN的推理速度提高了5-100倍。 （阅读更多）