Reducing Network Agnostophobia

Authors: Akshay Raj Dhamija, Manuel Günther, Terrance Boult

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on networks trained to classify classes from MNIST and CIFAR-10 show that our novel loss functions are significantly better at dealing with unknown inputs from datasets such as Devanagari, Not MNIST, CIFAR-100, and SVHN.
Researcher Affiliation Academia Akshay Raj Dhamija, Manuel G unther, and Terrance E. Boult Vision and Security Technology Lab, University of Colorado Colorado Springs {adhamija | mgunther | tboult} @ vast.uccs.edu
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes Our code is publicly available.1 1http://github.com/Vastlab/Reducing-Network-Agnostophobia
Open Datasets Yes Experiments on networks trained to classify classes from MNIST and CIFAR-10 show that our novel loss functions are significantly better at dealing with unknown inputs from datasets such as Devanagari, Not MNIST, CIFAR-100, and SVHN.
Dataset Splits No The paper does not provide specific train/validation/test dataset splits with percentages or sample counts for reproduction, nor does it explicitly mention the use of a dedicated validation set for model tuning.
Hardware Specification No The paper does not specify the hardware used to run experiments, such as specific GPU or CPU models, or details about the computing environment.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., Python 3.x, TensorFlow x.x, PyTorch x.x) for reproducing the experiments.
Experiment Setup No The paper does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or detailed training configurations in the main text.