Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Semi-supervised Learning with Ladder Networks
Authors: Antti Rasmus, Mathias Berglund, Mikko Honkala, Harri Valpola, Tapani Raiko
NeurIPS 2015 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We ran experiments both with the MNIST and CIFAR-10 datasets, where we attached the decoder both to fully-connected MLP networks and to convolutional neural networks. |
| Researcher Affiliation | Collaboration | Antti Rasmus and Harri Valpola The Curious AI Company, Finland; Mikko Honkala Nokia Labs, Finland; Mathias Berglund and Tapani Raiko Aalto University, Finland & The Curious AI Company, Finland |
| Pseudocode | Yes | Algorithm 1 Calculation of the output y and cost function C of the Ladder network |
| Open Source Code | Yes | The source code for all the experiments is available at https://github.com/arasmus/ladder. |
| Open Datasets | Yes | We ran experiments both with the MNIST and CIFAR-10 datasets |
| Dataset Splits | Yes | For evaluating semi-supervised learning, we randomly split the 60 000 training samples into 10 000sample validation set and used M = 50 000 samples as the training set. |
| Hardware Specification | No | No specific hardware details (e.g., GPU/CPU models, memory) used for running experiments are provided. The paper only mentions 'computational resources provided by the Aalto Science-IT project'. |
| Software Dependencies | No | The software for the simulations for this paper was based on Theano [32] and Blocks [33]. No specific version numbers for these software dependencies are provided. |
| Experiment Setup | Yes | We used the Adam optimization algorithm [14]. The initial learning rate was 0.002 and it was decreased linearly to zero during a ο¬nal annealing phase. The minibatch size was 100. |