用二进制编码让神经网络外推周期函数，无需知道具体公式。
Extrapolation of Periodic Functions Using Binary Encoding of Continuous Numerical Values
- 用归一化二进制编码处理连续数值输入
- 普通MLP在未见过的区间仍能准确外推周期信号
- 编码诱发比特相位表示，使模型位置无关学习
我们发现，二进制编码可使神经网络在训练范围之外成功外推周期函数。本文提出归一化基二编码（NB2E）用于连续数值的编码，并证明使用该编码方式，未经函数形式先验知识的普通多层感知机（MLP）能有效外推多种周期信号。内部激活分析显示，NB2E诱导出比特相位表示，使MLP能够独立于位置学习并外推信号结构。
原文摘要 · Abstract (English)
We report the discovery that binary encoding allows neural networks to extrapolate periodic functions beyond their training bounds. We introduce Normalized Base-2 Encoding (NB2E) as a method for encoding continuous numerical values and demonstrate that, using this input encoding, vanilla multi-layer perceptrons (MLP) successfully extrapolate diverse periodic signals without prior knowledge of their functional form. Internal activation analysis reveals that NB2E induces bit-phase representations, enabling MLPs to learn and extrapolate signal structure independently of position.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。