On Robust Concepts and Small Neural Nets

Authors: Amit Deshpande, Sushrut Karmalkar

ICLR 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We prove that any noise-stable boolean function on n boolean-valued input variables can be well-approximated by a two-layer linear threshold circuit with a small number of hidden-layer nodes and small weights, that depend only on the noise-stability and approximation parameters, and are independent of n. We also give a polynomial time learning algorithm that outputs a small two-layer linear threshold circuit that approximates such a given function. The universal approximation theorem of Hornik et al. (1989) and Cybenko (1992) provides a foundation to the mathematical theory of artificial neural networks.
Researcher Affiliation Collaboration Amit Deshpande Microsoft Research, Vigyan, 9 Lavelle Road, Bengaluru 560001, India amitdesh@microsoft.com Sushrut Karmalkar Department of Computer Science, The University of Texas at Austin, 2317 Speedway, Stop D9500 Austin, TX 78712, USA sushrutk@cs.utexas.edu
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access to source code for the methodology described.
Open Datasets No This is a theoretical paper and does not mention specific datasets used for training or public availability of any dataset.
Dataset Splits No This is a theoretical paper and does not provide specific dataset split information.
Hardware Specification No The paper does not provide any specific hardware details used for running experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers.
Experiment Setup No The paper is theoretical and does not include specific experimental setup details, hyperparameters, or training configurations.