The modern deep learning method based on backpropagation has surged in popularity and has been used in multiple domains and application areas. At the same time, there are other -- less-known -- machine learning algorithms with a mature and solid theoretical foundation whose performance remains unexplored. One such example is the brain-like Bayesian Confidence Propagation Neural Network (BCPNN). In this paper, we introduce StreamBrain -- a framework that allows neural networks based on BCPNN to be practically deployed in High-Performance Computing systems. StreamBrain is a domain-specific language (DSL), similar in concept to existing machine learning (ML) frameworks, and supports backends for CPUs, GPUs, and even FPGAs. We empirically demonstrate that StreamBrain can train the well-known ML benchmark dataset MNIST within seconds, and we are the first to demonstrate BCPNN on STL-10 size networks. We also show how StreamBrain can be used to train with custom floating-point formats and illustrate the impact of using different bfloat variations on BCPNN using FPGAs.

中文翻译：

---

StreamBrain：用于 CPU、GPU 和 FPGA 上类脑神经网络的 HPC 框架

基于反向传播的现代深度学习方法风靡一时，并已在多个领域和应用领域得到应用。与此同时，还有其他——鲜为人知的——机器学习算法具有成熟而坚实的理论基础，其性能仍有待探索。一个这样的例子是类似大脑的贝叶斯置信传播神经网络 (BCPNN)。在本文中，我们介绍了 StreamBrain——一个允许基于 BCPNN 的神经网络实际部署在高性能计算系统中的框架。StreamBrain 是一种领域特定语言 (DSL)，在概念上类似于现有的机器学习 (ML) 框架，并支持 CPU、GPU 甚至 FPGA 的后端。我们凭经验证明 StreamBrain 可以在几秒钟内训练著名的 ML 基准数据集 MNIST，我们是第一个在 STL-10 大小的网络上演示 BCPNN 的人。我们还展示了如何使用 StreamBrain 来训练自定义浮点格式，并说明在使用 FPGA 的 BCPNN 上使用不同 bfloat 变体的影响。