Reversible Architectures for Arbitrarily Deep Residual Neural Networks

Authors: Bo Chang, Lili Meng, Eldad Haber, Lars Ruthotto, David Begert, Elliot Holtham

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results demonstrate the efficacy of our architectures against several strong baselines on CIFAR-10, CIFAR-100 and STL-10 with superior or on-par state-of-the-art performance.
Researcher Affiliation Collaboration 1University of British Columbia, Vancouver, Canada. (bchang@stat.ubc.ca, menglili@cs.ubc.ca, haber@math.ubc.ca) 2Xtract Technologies Inc., Vancouver, Canada. (david@xtract.ai, elliot@xtract.ai) 3Emory University, Atlanta, USA. (lruthotto@emory.edu).
Pseudocode No The paper does not contain explicit pseudocode or algorithm blocks.
Open Source Code No The paper does not provide a link to source code or an explicit statement about releasing it.
Open Datasets Yes The CIFAR-10 dataset (Krizhevsky and Hinton 2009) consists of 50,000 training images and 10,000 testing images in 10 classes with 32 32 image resolution.
Dataset Splits No The paper specifies training and test set sizes but does not explicitly mention a separate validation set split or its size.
Hardware Specification Yes The CIFAR-10/100 and STL-10 experiments are evaluated on a desktop with an Intel Quad-Core i5 CPU and a single Nvidia 1080 Ti GPU.
Software Dependencies No The paper mentions 'TensorFlow library' but does not specify a version number.
Experiment Setup Yes The learning rate is initialized to be 0.1 and decayed by a factor of 10 at 80, 120 and 160 training epochs. The total training step is 80K. The weight decay constant is set to 2 10 4, weight smoothness decay is 2 10 4 and the momentum is set to 0.9.