We introduce a novel spiking neural network model for learning distributed internal representations from data in an unsupervised procedure. We achieved this by transforming the non-spiking feedforward Bayesian Confidence Propagation Neural Network (BCPNN) model, employing an online correlation-based Hebbian-Bayesian learning and rewiring mechanism, shown previously to perform representation learning, into a spiking neural network with Poisson statistics and low firing rate comparable to in vivo cortical pyramidal neurons. We evaluated the representations learned by our spiking model using a linear classifier and show performance close to the non-spiking BCPNN, and competitive with other Hebbian-based spiking networks when trained on MNIST and F-MNIST machine learning benchmarks.

翻译：我们提出了一种新颖的脉冲神经网络模型，用于通过无监督过程从数据中学习分布式内部表示。这是通过将非脉冲前馈贝叶斯置信传播神经网络（BCPNN）模型——该模型采用在线相关性驱动的Hebbian-贝叶斯学习与重连机制，先前已被证明能有效进行表示学习——转换为脉冲神经网络实现的，该网络具有泊松统计特性和与体内皮层锥体神经元相当的低发放率。我们利用线性分类器评估了脉冲模型学习到的表示，结果表明其性能接近非脉冲BCPNN，并且在MNIST和F-MNIST机器学习基准测试中，与其他基于Hebbian的脉冲网络相比具有竞争力。