AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

The power of deeper networks for expressing natural functions

David Rolnick, Max Tegmark

ICLR 2018 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 117 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use a deep network instead of a single hidden layerFeedforward networks approximating multivariate monomials · Multivariate monomialneurons required: \prod_{i=1}^n (r_i + 1) -> \le \sum_{i=1}^n (7\lceil\log_2(r_i)\rceil + 4)Improved
Use a deep network instead of a single hidden layerFeedforward networks approximating sparse multivariate polynomials · Sparse multivariate polynomialneurons required: \ge \frac{1}{c}\max_j \munif_1(q_j) -> \le \sum_j \munif(q_j)Improved
Use a deep network instead of a single hidden layerFeedforward networks approximating x^d · Univariate monomial x^dneurons required: d + 1 -> \le 7\lceil\log_2(d)\rceilImproved
Use a fixed neuron count while changing weights for increasingly accurate approximationsFeedforward networks approximating degree-d polynomials · Polynomial uniform approximationneurons required as ε approaches zeroNo clear effect
Use ReLU activation rather than an activation with the required nonzero Taylor coefficientsFixed-size network approximation of nonlinear polynomials · Polynomial uniform approximationneurons required as ε approaches zeroHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy