Neural networks that can capture key principles underlying brain computation offer exciting new opportunities for developing artificial intelligence and brain-like computing algorithms. Such networks remain biologically plausible while leveraging localized forms of synaptic learning rules and modular network architecture found in the neocortex. Compared to backprop-driven deep learning approches, they provide more suitable models for deploying on neuromorphic hardware and have greater potential for scalability on large-scale computing clusters. The development of such brain-like neural networks depends on having a learning procedure that can build effective internal representations from data. In this work, we introduce and evaluate a brain-like neural network model capable of unsupervised representation learning. It builds on the Bayesian Confidence Propagation Neural Network (BCPNN), which has earlier been implemented as abstract as well as biophyscially detailed recurrent attractor neural networks explaining various cortical associative memory phenomena. Here we developed a feedforward BCPNN model to perform representation learning by incorporating a range of brain-like attributes derived from neocortical circuits such as cortical columns, divisive normalization, Hebbian synaptic plasticity, structural plasticity, sparse activity, and sparse patchy connectivity. The model was tested on a diverse set of popular machine learning benchmarks: grayscale images (MNIST, Fashion-MNIST), RGB natural images (SVHN, CIFAR-10), QSAR (MUV, HIV), and malware detection (EMBER). The performance of the model when using a linear classifier to predict the class labels fared competitively with conventional multi-layer perceptrons and other state-of-the-art brain-like neural networks.

翻译：能够捕捉大脑计算核心原则的神经网络为发展人工智能与类脑计算算法提供了新的机遇。此类网络在保持生物合理性的同时，充分利用了新皮层中存在的局部化突触学习规则与模块化网络架构。相较于基于反向传播的深度学习方法，它们更适合部署于神经形态硬件，并在大规模计算集群上具有更强的可扩展性潜力。开发此类类脑神经网络的关键在于建立能从数据中构建有效内部表征的学习程序。本文提出并评估了一种具备无监督表示学习能力的类脑神经网络模型。该模型基于贝叶斯置信传播神经网络（BCPNN），该网络此前已通过抽象模型和生物物理精细的循环吸引子网络形式实现，能够解释多种皮层联想记忆现象。我们通过整合新皮层回路的多种类脑特性（包括皮层柱、除法归一化、赫布突触可塑性、结构可塑性、稀疏活动及稀疏斑块连接性），开发了用于表示学习的前馈BCPNN模型。该模型在多种主流机器学习基准数据集上进行了测试：灰度图像（MNIST、Fashion-MNIST）、RGB自然图像（SVHN、CIFAR-10）、QSAR（MUV、HIV）及恶意软件检测（EMBER）。采用线性分类器预测类别标签时，该模型的性能与传统多层感知器及其他前沿类脑神经网络相比具有竞争力。