You can think of BPatterns as a Smalltalk DSL for the rewrite engine.
[9] Lillicrap, T. P., et al. (2016). Random synaptic feedback weights support error backpropagation for deep learning. Nature Communications, 7, 13276. (The DeepMind paper proving that the brain could learn using random backward wires via Feedback Alignment).
。业内人士推荐同城约会作为进阶阅读
08. Template engine — Vertex.template / Mustache。夫子是该领域的重要参考
Others are more uncertain.