As 2020 drew to a close, I was thinking about what lessons we have learned about software engineering (SE) for artificial intelligence (AI)-things that we can believe now but, in the last century, would have seemed somewhat shocking. One very surprising lesson, at least for me, is the success of the very complex and very simple. At the complex end, there is now much evidence for the value of deep learners for high-dimensional software engineering problems. For example, consider signal processing for autonomous cars. When reasoning over (say) 10,000 wavelets collected from a vision system, then deep learning can automate much of the engineering required to cover all those data.

中文翻译：

---

令人震惊的简单：“键”可为SE提供更好的AI

到2020年即将结束时，我正在思考我们从人工智能（AI）的软件工程（SE）中学到的经验教训，这些东西我们现在可以相信，但在上个世纪，这似乎有些令人震惊。至少对我来说，一个非常令人惊讶的教训是，非常复杂和非常简单的成功。在复杂的一端，现在有很多证据表明深度学习者对于高维软件工程问题的价值。例如，考虑自动驾驶汽车的信号处理。当推理（说）从视觉系统收集的10,000个小波时，深度学习可以自动完成涵盖所有这些数据所需的大部分工程。