TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Are partial derivatives the computational primitives of deep neural networks?

3 点作者 aidanrocke超过 5 年前

1 comment

aidanrocke超过 5 年前
tl;dr<p>1. The typical deep neural network tutorial introduces deep networks as compositions of nonlinearities and affine transforms.<p>2. In fact, a deep network with relu activation simplifies to a linear combination of affine transformations with compact support. But, why would affine transformations be useful?<p>3. After recent discussions on Twitter it occurred to me that the reason why they work is that they are actually first-order Taylor approximations of a suitable analytic function.<p>4. What is really cool about this is that by this logic partial derivatives, i.e. Jacobians, are computational primitives for both inference and learning.<p>5. I think this also provides insight into how deep networks approximate functions. They approximate the intrinsic geometry of a relation using piece-wise linear functions.<p>This works because a suitable polynomial approximation exists and all polynomials are locally Lipschitz.