A Discriminative Gaussian Mixture Model with Sparsity
Authors: Hideaki Hayashi, Seiichi Uchida
ICLR 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results demonstrated that the proposed method outperformed the existing softmax-based discriminative models. To evaluate the capability of the SDGM quantitatively, we conducted a classification experiment using benchmark datasets. |
| Researcher Affiliation | Academia | Hideaki Hayashi & Seiichi Uchida Department of Advanced Information Technology Kyushu University 744, Motooka, Nishi-ku, Fukuoka, 819-0395 JAPAN {hayashi,uchida}@ait.kyushu-u.ac.jp |
| Pseudocode | Yes | Algorithm 1: Learning algorithm of the SDGM |
| Open Source Code | No | The paper does not provide any concrete access to source code (no specific repository link, explicit code release statement, or mention of code in supplementary materials). |
| Open Datasets | Yes | The datasets used in this experiment were Ripley s synthetic data (Ripley 2006) and four datasets cited from (R atsch et al. 2001); Banana, Waveform, Titanic, and Breast Cancer. ... MNIST: This dataset includes 10 classes of handwritten binary digit images of size 28 28 (Le Cun et al. 1998). ... Fashion-MNIST (Xiao et al. 2017) ... CIFAR-10 and CIFAR-100 (Krizhevsky & Hinton 2009) ... Image Net classification dataset (Russakovsky et al. 2015) |
| Dataset Splits | Yes | Ripley is a synthetic dataset... 250 and 1,000 samples are provided for training and test, respectively. ... The remaining four datasets... contain 100 training/test splits... MNIST... We used 60,000 images as training data and 10,000 images as testing data. ... Fashion-MNIST... It includes 60,000 images for training data and 10,000 images for testing data. ... CIFAR-10 and CIFAR-100... There are 50,000 training images and 10,000 test images for both datasets. ... Image Net... It consists of 1,281,167 training images, 50,000 validation images, and 100,000 test images. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as exact GPU/CPU models, processor types, or memory amounts used for running the experiments. It only mentions using CNN architectures like Dense Net and Mobile Net. |
| Software Dependencies | No | The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | No | The paper describes the CNN architectures used for image classification, such as 'simple CNN that consists of five convolutional layers with four max pooling layers' and 'Dense Net with a depth of 40 and a growth rate of 12'. It also mentions employing 'approximated sparse Bayesian learning based on Gaussian dropout'. However, it does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or detailed training configurations. |