Deep Information Propagation

Authors: Samuel S. Schoenholz, Justin Gilmer, Surya Ganguli, Jascha Sohl-Dickstein

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

Reproducibility Variable Result LLM Response
Research Type Experimental To test this ansatz we train ensembles of deep, fully connected, feed-forward neural networks of varying depth on MNIST and CIFAR10, with and without dropout. Our results confirm that neural networks are trainable precisely when their depth is not much larger than ξc.
Researcher Affiliation Collaboration Samuel S. Schoenholz Google Brain Justin Gilmer Google Brain Surya Ganguli Stanford University Jascha Sohl-Dickstein Google Brain
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes To test this ansatz we train ensembles of deep, fully connected, feed-forward neural networks of varying depth on MNIST and CIFAR10, with and without dropout.
Dataset Splits No The paper mentions training on MNIST and CIFAR10, but does not explicitly provide specific dataset split information (percentages or counts) or reference predefined splits for validation.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes We train these networks using Stochastic Gradient Descent (SGD) and RMSProp on MNIST and CIFAR10. We use a learning rate of 10-3 for SGD when L <= 200, 10-4 for larger L, and 10-5 for RMSProp. These learning rates were selected by grid search between 10-6 and 10-2 in exponentially spaced steps of size 10.