Gaussian Cardinality Restricted Boltzmann Machines

Authors: Cheng Wan, Xiaoming Jin, Guiguang Ding, Dou Shen

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on two real world data sets justify the effectiveness of the proposed method and its superiority over Ca RBM in terms of classification accuracy.
Researcher Affiliation Collaboration School of Software, Tsinghua University, Beijing, China Baidu Corporation, Beijing, China
Pseudocode Yes Algorithm 1 Learning Algorithm of GC-RBM on Pretraining Phase
Open Source Code No The paper does not provide any explicit statement about releasing source code or a link to a code repository.
Open Datasets Yes The experiments were conducted on MNIST and CIFAR10 (Krizhevsky and Hinton 2009).
Dataset Splits No The paper specifies training and test set sizes for MNIST and CIFAR-10 (e.g., "60000 images for training and 10000 images for test" for MNIST), but does not explicitly mention a validation split or its size.
Hardware Specification No The paper does not specify any hardware details such as GPU models, CPU types, or memory specifications used for running the experiments.
Software Dependencies No The paper does not mention any specific software libraries, frameworks, or their version numbers used in the implementation or experimentation.
Experiment Setup Yes The μ and σ in GC-RBM and naive GC-RBM were assigned to μ {10, 20, ..., 100}, σ2 {9, 25, 100}. In order to have comparisons among three models, the k in Ca RBM was assigned to the same values as the μ in our Gaussian thresholds models. We applied the Ca RBM, naive GC-RBM and GC-RBM to train a three layers (784-100-10) feed-forward neural network...