Generalization in multitask deep neural classifiers: a statistical physics approach

Authors: Anthony Ndirango, Tyler Lee

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We discuss the validity of our theoretical results in comparison to a comprehensive suite of numerical experiments.
Researcher Affiliation Industry Tyler Lee Intel AI Lab tyler.p.lee@intel.com Anthony Ndirango Intel AI Lab anthony.ndirango@intel.com
Pseudocode No The paper describes mathematical derivations and processes but does not include any pseudocode or clearly labeled algorithm blocks.
Open Source Code No Code supporting this paper is available upon request
Open Datasets No The paper describes a 'student-teacher setup' where data is generated by a teacher network, and does not mention or provide access information for a publicly available dataset.
Dataset Splits No The paper mentions 'validation error' in Figure 1 caption, implying a validation set was used, but does not provide specific percentages or counts for training, validation, or test dataset splits.
Hardware Specification No The paper acknowledges 'the compute infrastructure that made the empirical portions of this work possible' but does not provide specific hardware details like CPU/GPU models or types of accelerators.
Software Dependencies No The paper does not list specific software dependencies with version numbers used for the experiments.
Experiment Setup Yes 1/ = 10 3 is the learning rate