Katharina Flügel, Daniel Coquelin, Marie Weiel, Charlotte Debus, Achim Streit...
TL;DR研究提出了一种名为Feed-Forward with delayed Feedback (F$^3$)的算法，它有效地解决了权重传输和更新锁定等核心问题，实现了生物合理性和计算效率，将生物合理性算法和反向传播算法之间的预测性能差距降低了96%，为低能耗训练和并行化开辟了新的前景。
Abstract
backpropagation has long been criticized for being biologically implausible, relying on concepts that are not viable in natural learning processes. This paper proposes an alternative approach to solve two core issues, i.e., →