架构师（The Architect）：直接在微软 Excel 中实现深度学习数学的交互式可视化工具
The Architect: Interactive Visualization of Deep Learning Mathematics Directly in Microsoft Excel
查看机构详情
- University of Colorado Boulder（科罗拉多大学博尔德分校）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
该研究提出名为 The Architect 的系统，可将微软 Excel 变为深度学习数学交互式视图，支持可视化神经网络计算、生成 PyTorch 代码片段，助力理解小型神经网络。
中文摘要 AI 辅助
我们提出了 The Architect，一个可将微软 Excel 转变为深度学习数学交互式视图的系统。用户在一张紧凑表格中描述神经网络，随后该系统会生成一个工作簿，展示完整的前向传播过程，且在用户请求时还会展示反向传播过程与参数更新。计算值以实时电子表格公式呈现，而输入、权重、标签、超参数等用户可控值则保持可编辑状态。Excel 会通过其重新计算引擎对依赖计算进行响应式更新。大多数深度学习工具会将数值细节隐藏在库调用之后，许多可视化工具仅展示架构图或训练摘要，却不会暴露模型的完整算术运算。The Architect 聚焦于这一缺失的中间层，它将矩阵、激活函数、损失、梯度及更新内容可视化为可检查的电子表格区域，并为用户自然操作的数值提供可编辑控件。该系统还会生成对齐的 PyTorch 代码片段，帮助用户将公式与实现建立关联。本报告描述了 The Architect 的动机、设计、实现及用例，展示了该系统如何支持入门级算术追踪、学习率探索、死亡 ReLU 的诊断以及消失梯度的检查。其核心思路十分简单：电子表格已支持公式、直接编辑、响应式重新计算及表格布局，这些特性使其成为理解小型教育型与诊断型神经网络计算过程的有用媒介。
英文摘要
We present The Architect, a system that turns Microsoft Excel into an interactive view of deep learning mathematics. A user describes a neural network in a compact table. The system then generates a workbook that shows the full forward pass and, when requested, the backward pass and parameter updates. Computed values appear as live spreadsheet formulas, while user-controlled values such as inputs, weights, labels, and hyperparameters remain editable. Excel reactively updates the dependent computations through its recalculation engine. Most deep learning tools hide the numerical details behind library calls. Many visualization tools show architecture diagrams or training summaries, but they do not expose the full arithmetic of the model. The Architect focuses on that missing middle layer. It makes matrices, activations, losses, gradients, and updates visible as inspectable spreadsheet regions, with editable controls for values users naturally manipulate. The system also produces aligned PyTorch snippets, which helps users connect formulas to implementation. This report describes the motivation, design, implementation, and use cases of The Architect. We show how the system supports introductory arithmetic tracing, learning-rate exploration, diagnosis of dying ReLU, and inspection of vanishing gradients. The main idea is simple: spreadsheets already support formulas, direct editing, reactive recomputation, and tabular layout. These properties make them a useful medium for understanding how small educational and diagnostic neural networks compute.
