Chollet这段历史补课很关键：别以为端到端神经网络是终点，现在风向已经是神经符号系统了。
François Chollet回顾AI模型架构的关键转折：过去高性能模型多为端到端神经模型，输入输出都是向量。当时学界普遍推崇“可微分编程”，主张把更多逻辑交给神经网络。而当前实际流行的是重神经符号系统，模型本身包含符号层。
critical history and context that a lot of people have conveniently forgotten
critical history and context that a lot of people have conveniently forgotten François Chollet @fchollet For a very long time most high-performing AI models were end-to-end neural models; vector input -> vector output, with only ultra-thin symbolic preprocessing and postprocessing layers (e.g. label decoding). For many, it seemed that moving more and more logic to the end-to-end neural model was the way of the future. "Differentiable programming". But what we have now is heavy neurosymbolic systems where the model itself is symbolic. 🔗 View Quoted Tweet 💬 3 🔄 2 ❤️ 12 👀 2647 📊 4 ⚡