A Probabilistic Framework for Deep Learning
Authors: Ankit B. Patel, Minh Tan Nguyen, Richard Baraniuk
NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 4 Experimental Results We evaluate the DRMM and DRFM s performance on the MNIST dataset, a standard digit classification benchmark with a training set of 60,000 28 28 labeled images and a test set of 10,000 labeled images. We also evaluate the DRMM s performance on CIFAR10, a dataset of natural objects which include a training set of 50,000 32 32 labeled images and a test set of 10,000 labeled images. |
| Researcher Affiliation | Academia | Ankit B. Patel Baylor College of Medicine, Rice University ankitp@bcm.edu,abp4@rice.edu Tan Nguyen Rice University mn15@rice.edu Richard G. Baraniuk Rice University richb@rice.edu |
| Pseudocode | Yes | Algorithm 1 Hard EM and EG Algorithms for the DRMM |
| Open Source Code | No | The paper does not contain an explicit statement that the source code for the described methodology is publicly available, nor does it provide a link to a code repository. |
| Open Datasets | Yes | We evaluate the DRMM and DRFM s performance on the MNIST dataset, a standard digit classification benchmark with a training set of 60,000 28 28 labeled images and a test set of 10,000 labeled images. We also evaluate the DRMM s performance on CIFAR10, a dataset of natural objects which include a training set of 50,000 32 32 labeled images and a test set of 10,000 labeled images. |
| Dataset Splits | Yes | We evaluate the DRMM and DRFM s performance on the MNIST dataset, a standard digit classification benchmark with a training set of 60,000 28 28 labeled images and a test set of 10,000 labeled images. For semi-supervised training, we use a randomly chosen subset of NL = 100, 600, 1K, and 3K labeled images and NU = 60K unlabeled images from the training and validation set. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory amounts, or cloud instances) used for conducting the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., library names with versions) needed to replicate the experiment. |
| Experiment Setup | No | The main text describes the general training procedure (e.g., using the Generalized EM algorithm with gradient descent) and states that "Configurations of our models and the corresponding DCNs are provided in the Appendix I." However, it does not explicitly provide specific hyperparameter values or detailed system-level training settings within the main body of the paper. |