We describe a method to train spiking deep networks that can be run using
leaky integrate-and-fire (LIF) neurons, achieving state-of-the-art results for
spiking LIF networks on five datasets, including the large ImageNet ILSVRC-2012
benchmark. Our method for transforming deep artificial neural networks into
spiking networks is scalable and works with a wide range of neural
nonlinearities. We achieve these results by softening the neural response
function, such that its derivative remains bounded, and by training the network
with noise to provide robustness against the variability introduced by spikes.
Our analysis shows that implementations of these networks on neuromorphic
hardware will be many times more power-efficient than the equivalent
non-spiking networks on traditional hardware.

本文介绍了一种方法，该方法可以训练使用 Leaky Integrate-and-Fire（LIF）神经元的脉冲深度网络，并在包括大型 ImageNet ILSVRC-2012 基准测试在内的五个数据集上取得了最先进的结果。该方法可扩展，并适用于各种神经非线性。通过软化神经响应函数以使其导数保持有界，并通过噪声训练网络，我们实现了这些结果，以提高其承受由脉冲引入的变异性的鲁棒性。我们的分析表明，在神经形态硬件上实现这些网络将比传统硬件上等效的非脉冲网络更加节能。

为神经形态硬件训练脉冲深度网络

Training Spiking Deep Networks for Neuromorphic Hardware

We present a spike-based unsupervised regenerative learning scheme to train
Spiking Deep Networks (SpikeCNN) for object recognition problems using
biologically realistic leaky integrate-and-fire neurons. The training
methodology is based on the Auto-Encoder learning model wherein the
hierarchical network is trained layer wise using the encoder-decoder principle.
Regenerative learning uses spike-timing information and inherent latencies to
update the weights and learn representative levels for each convolutional layer
in an unsupervised manner. The features learnt from the final layer in the
hierarchy are then fed to an output layer. The output layer is trained with
supervision by showing a fraction of the labeled training dataset and performs
the overall classification of the input. Our proposed methodology yields
0.92%/29.84% classification error on MNIST/CIFAR10 datasets which is comparable
with state-of-the-art results. The proposed methodology also introduces
sparsity in the hierarchical feature representations on account of event-based
coding resulting in computationally efficient learning.

提出一种基于脉冲的非监督递归学习方案，用于使用生物学上可信的漏积分放电神经元训练 Spiking Deep Networks (SpikeCNN) 进行目标识别问题。训练方法基于自编码器学习模型，其中分层网络使用编码器 - 解码器原理逐层训练。递归学习使用脉冲时序信息和固有延迟以无监督方式更新权重并学习每个卷积层的代表水平。从层次结构中学到的特征然后馈送到一个输出层。所提议的方法在 MNIST/CIFAR10 数据集上产生了与现有技术水平相当的分类错误率，并通过基于事件的编码引入稀疏性来提高计算效率。

突触深度网络无监督再生式学习层次化特征以进行对象识别

Unsupervised Regenerative Learning of Hierarchical Features in Spiking  Deep Networks for Object Recognition

We train spiking deep networks using leaky integrate-and-fire (LIF) neurons,
and achieve state-of-the-art results for spiking networks on the CIFAR-10 and
MNIST datasets. This demonstrates that biologically-plausible spiking LIF
neurons can be integrated into deep networks can perform as well as other
spiking models (e.g. integrate-and-fire). We achieved this result by softening
the LIF response function, such that its derivative remains bounded, and by
training the network with noise to provide robustness against the variability
introduced by spikes. Our method is general and could be applied to other
neuron types, including those used on modern neuromorphic hardware. Our work
brings more biological realism into modern image classification models, with
the hope that these models can inform how the brain performs this difficult
task. It also provides new methods for training deep networks to run on
neuromorphic hardware, with the aim of fast, power-efficient image
classification for robotics applications.

使用 LIF 神经元训练脉冲深度网络，并在 CIFAR-10 和 MNIST 数据集上实现了最先进的结果。通过软化 LIF 响应函数并添加噪声，我们的方法旨在实现在神经形态硬件上训练深度网络的快速、高效的图像分类。