Deconstructing the Ladder Network Architecture

Authors: Mohammad Pezeshki, Linxi Fan, Philemon Brakel, Aaron Courville, Yoshua Bengio

ICML 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental This paper presents an extensive experimental investigation of variants of the Ladder Network in which we replaced or removed individual components to learn about their relative importance.
Researcher Affiliation Academia Mohammad Pezeshki MOHAMMAD.PEZESHKI@UMONTREAL.CA Linxi Fan LINXI.FAN@COLUMBIA.EDU Phil emon Brakel PBPOP3@GMAIL.COM Aaron Courville AARON.COURVILE@UMONTREAL.CA Yoshua Bengio YOSHUA.BENGIO@UMONTREAL.CA Universit e de Montr eal, Columbia University, CIFAR
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link indicating the release of open-source code for the described methodology.
Open Datasets Yes The experimental setup includes two semi-supervised classification tasks with 100 and 1000 labeled examples and a fully-supervised classification task with 60000 labeled examples for Permutation-Invariant MNIST handwritten digit classification.
Dataset Splits No The paper mentions that 'The test set is not used during all the hyperparameter search and tuning' and that 'Hyperparameters... are tuned separately for each variant and each experiment setting', implying the use of a validation set, but it does not specify the exact split percentages or sample counts for training, validation, and testing.
Hardware Specification No The paper does not provide any specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions algorithms and techniques (e.g., 'ADAM optimization algorithm', 'Batch Normalization'), but it does not specify any software dependencies with version numbers (e.g., Python, TensorFlow, PyTorch versions).
Experiment Setup Yes All variants and the vanilla Ladder Network itself are trained using the ADAM optimization algorithm (Kingma & Ba, 2014) with a learning rate of 0.002 for 100 iterations followed by 50 iterations with a learning rate decaying linearly to 0. Hyperparameters including the standard deviation of the noise injection and the denoising weights at each layer are tuned separately for each variant and each experiment setting (100-, 1000-, and fully-labeled).