{ "ok": true, "doi": "10.46243/jst.2021.v6.i3.pp169-177", "events": [ { "seq": 1, "kind": "register", "at": "2026-09-29 22:00:41", "by": "Administrator (admin)", "by_kind": "user", "note": "registered at Crossref; record read from api.crossref.org", "changes": [ { "path": "abstract.lang", "from": null, "to": "en" }, { "path": "abstract.value", "from": null, "to": "In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between the success of CNNs for supervised learning and unsupervised learning. We introduce a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrate that they are a strong candidate for unsupervised learning. Training on various image datasets, we show convincing evidence that our deep convolutional adversarial pair learns a hierarchy of representations from object parts to scenes in both the generator and discriminator. The generator uses tf.keras.layers.conv2Dtranspose (up sampling) layers to produce an image from a seed (random noise). Start with a dense layer that takes this seed as input, then up sample several times until you reach the desired image size of 28x28x1. The discriminator is a CNN-based image classifier. The model will be trained to output positive values for real images, and negative values for fake images. We define the Generator loss and the discriminator loss and we finally we get new images that look similar to our input(MNIST) images." }, { "path": "agents.0.name.family", "from": null, "to": "Lakshmi" }, { "path": "agents.0.name.given", "from": null, "to": "S. Vijaya" }, { "path": "agents.0.role", "from": null, "to": "author" }, { "path": "agents.0.sequence", "from": null, "to": "first" }, { "path": "agents.1.name.family", "from": null, "to": "Raju Ganaraju" }, { "path": "agents.1.name.given", "from": null, "to": "Vallik Sai Ganesh" }, { "path": "agents.1.role", "from": null, "to": "author" }, { "path": "agents.1.sequence", "from": null, "to": "additional" }, { "path": "agents.2.name.org", "from": null, "to": "Longman Publishers" }, { "path": "agents.2.role", "from": null, "to": "publisher" }, { "path": "characters.0", "from": null, "to": "Language" }, { "path": "container.identifiers.0.medium", "from": null, "to": "electronic" }, { "path": "container.identifiers.0.type", "from": null, "to": "ISSN" }, { "path": "container.identifiers.0.value", "from": null, "to": "2456-5660" }, { "path": "container.issue", "from": null, "to": "03" }, { "path": "container.pages.first", "from": null, "to": "169" }, { "path": "container.pages.last", "from": null, "to": "177" }, { "path": "container.titles.0.type", "from": null, "to": "PrincipalTitle" }, { "path": "container.titles.0.value", "from": null, "to": "Journal of Science & Technology" }, { "path": "container.type", "from": null, "to": "Journal" }, { "path": "container.volume", "from": null, "to": "06" }, { "path": "dates.date_type", "from": null, "to": "PublicationDate" }, { "path": "dates.online", "from": null, "to": "2021-06-02" }, { "path": "dates.published", "from": null, "to": "2021-06-02" }, { "path": "doi", "from": null, "to": "10.46243/jst.2021.v6.i3.pp169-177" }, { "path": "format", "from": null, "to": "smartscholars-doi-metadata/1.0" }, { "path": "identifiers.0.type", "from": null, "to": "DOI" }, { "path": "identifiers.0.value", "from": null, "to": "10.46243/jst.2021.v6.i3.pp169-177" }, { "path": "language", "from": null, "to": "en" }, { "path": "license.applies_to", "from": null, "to": "vor" }, { "path": "license.start", "from": null, "to": "2021-06-02" }, { "path": "license.url", "from": null, "to": "https://creativecommons.org/licenses/by/4.0/" }, { "path": "links.0.primary", "from": null, "to": true }, { "path": "links.0.return_type", "from": null, "to": "text/html" }, { "path": "links.0.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/view/854" }, { "path": "links.1.purpose", "from": null, "to": "text-mining" }, { "path": "links.1.return_type", "from": null, "to": "application/pdf" }, { "path": "links.1.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/download/854/781" }, { "path": "links.2.purpose", "from": null, "to": "text-mining" }, { "path": "links.2.return_type", "from": null, "to": "application/xml" }, { "path": "links.2.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/download/854/2432" }, { "path": "links.3.purpose", "from": null, "to": "similarity-checking" }, { "path": "links.3.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/view/854/781" }, { "path": "modes.0", "from": null, "to": "Visual" }, { "path": "record.issue_number", "from": null, "to": 1 }, { "path": "record.registered", "from": null, "to": "2026-09-12" }, { "path": "record.registrant", "from": null, "to": "Longman Publishers" }, { "path": "record.source", "from": null, "to": "crossref-api" }, { "path": "record.source_agency", "from": null, "to": "Crossref (member 25296)" }, { "path": "record.updated", "from": null, "to": "2026-09-20" }, { "path": "references.0.key", "from": null, "to": "ref1" }, { "path": "references.0.unstructured", "from": null, "to": "Understanding Generative Adversarial Networks (GANs). (2019). Retrieved from https://towardsdatascience.com/understandinggenerative-adversarial-networks-gans-cd6e4651a29" }, { "path": "references.1.key", "from": null, "to": "ref2" }, { "path": "references.1.unstructured", "from": null, "to": "Chollet, F. Deep learning with Python" }, { "path": "references.10.doi", "from": null, "to": "10.1109/cvpr.2009.5206848" }, { "path": "references.10.key", "from": null, "to": "ref11" }, { "path": "references.10.unstructured", "from": null, "to": "Deng, Jia, Dong, Wei, Socher, Richard, Li, Li-Jia, Li, Kai, and Fei-Fei, Li. Imagenet: A large-scale hierarchical image database. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pp. 248–255. IEEE, 2009" }, { "path": "references.2.key", "from": null, "to": "ref3" }, { "path": "references.2.unstructured", "from": null, "to": "Radford, A., Metz, L., &Chintala, S. (2016). Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. ICLR 2016" }, { "path": "references.3.key", "from": null, "to": "ref4" }, { "path": "references.3.unstructured", "from": null, "to": "Denton, Emily, Chintala, Soumith, Szlam, Arthur, and Fergus, Rob. Deep generative image models using a laplacian pyramid of adversarial networks. arXiv preprint arXiv:1506.05751, 2015" }, { "path": "references.4.doi", "from": null, "to": "10.1109/cvpr.2015.7298761" }, { "path": "references.4.key", "from": null, "to": "ref5" }, { "path": "references.4.unstructured", "from": null, "to": "Dosovitskiy, Alexey, Springenberg, Jost Tobias, and Brox, Thomas. Learning to generate chairs with convolutional neural networks. arXiv preprint arXiv:1411.5928, 2014" }, { "path": "references.5.key", "from": null, "to": "ref6" }, { "path": "references.5.unstructured", "from": null, "to": "Danilo Jimenez Rezende, Shakir Mohamed, and DaanWierstra, “Stochastic Backpropagation and Approximate Inference in Deep Generative Models,” arXiv (2014)" }, { "path": "references.6.key", "from": null, "to": "ref7" }, { "path": "references.6.unstructured", "from": null, "to": "Diederik P. Kingma and Max Welling, “Auto-Encoding Variational Bayes, arXiv (2013), https://arxiv.org/ abs/1312.6114" }, { "path": "references.7.key", "from": null, "to": "ref8" }, { "path": "references.7.unstructured", "from": null, "to": "Bergstra, James and Bengio, Yoshua. Random search for hyper-parameter optimization. JMLR, 2012" }, { "path": "references.8.doi", "from": null, "to": "10.1007/978-3-642-35289-8_30" }, { "path": "references.8.key", "from": null, "to": "ref9" }, { "path": "references.8.unstructured", "from": null, "to": "Coates, Adam and Ng, Andrew Y. Learning feature representations with k-means. In Neural Networks: Tricks of the Trade, pp. 561–580. Springer, 2012" }, { "path": "references.9.key", "from": null, "to": "ref10" }, { "path": "references.9.unstructured", "from": null, "to": "Coates, Adam and Ng, Andrew. Selecting receptive fields in deep networks. NIPS, 2011" }, { "path": "referent", "from": null, "to": "Creation" }, { "path": "structural_type", "from": null, "to": "Digital" }, { "path": "titles.0.lang", "from": null, "to": "en" }, { "path": "titles.0.type", "from": null, "to": "PrincipalTitle" }, { "path": "titles.0.value", "from": null, "to": "Deep Convolutional Generative Adversial Network on MNIST Dataset" }, { "path": "type", "from": null, "to": "JournalArticle" } ], "record_after": { "format": "smartscholars-doi-metadata/1.0", "doi": "10.46243/jst.2021.v6.i3.pp169-177", "referent": "Creation", "type": "JournalArticle", "structural_type": "Digital", "modes": [ "Visual" ], "characters": [ "Language" ], "titles": [ { "value": "Deep Convolutional Generative Adversial Network on MNIST Dataset", "type": "PrincipalTitle", "lang": "en" } ], "identifiers": [ { "type": "DOI", "value": "10.46243/jst.2021.v6.i3.pp169-177" } ], "agents": [ { "role": "author", "name": { "given": "S. Vijaya", "family": "Lakshmi" }, "sequence": "first" }, { "role": "author", "name": { "given": "Vallik Sai Ganesh", "family": "Raju Ganaraju" }, "sequence": "additional" }, { "role": "publisher", "name": { "org": "Longman Publishers" } } ], "dates": { "published": "2021-06-02", "date_type": "PublicationDate", "online": "2021-06-02" }, "language": "en", "container": { "type": "Journal", "titles": [ { "value": "Journal of Science & Technology", "type": "PrincipalTitle" } ], "identifiers": [ { "type": "ISSN", "value": "2456-5660", "medium": "electronic" } ], "volume": "06", "issue": "03", "pages": { "first": "169", "last": "177" } }, "links": [ { "url": "https://www.jst.org.in/index.php/pub/article/view/854", "return_type": "text/html", "primary": true }, { "url": "https://www.jst.org.in/index.php/pub/article/download/854/781", "purpose": "text-mining", "return_type": "application/pdf" }, { "url": "https://www.jst.org.in/index.php/pub/article/download/854/2432", "purpose": "text-mining", "return_type": "application/xml" }, { "url": "https://www.jst.org.in/index.php/pub/article/view/854/781", "purpose": "similarity-checking" } ], "abstract": { "value": "In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between the success of CNNs for supervised learning and unsupervised learning. We introduce a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrate that they are a strong candidate for unsupervised learning. Training on various image datasets, we show convincing evidence that our deep convolutional adversarial pair learns a hierarchy of representations from object parts to scenes in both the generator and discriminator. The generator uses tf.keras.layers.conv2Dtranspose (up sampling) layers to produce an image from a seed (random noise). Start with a dense layer that takes this seed as input, then up sample several times until you reach the desired image size of 28x28x1. The discriminator is a CNN-based image classifier. The model will be trained to output positive values for real images, and negative values for fake images. We define the Generator loss and the discriminator loss and we finally we get new images that look similar to our input(MNIST) images.", "lang": "en" }, "license": { "url": "https://creativecommons.org/licenses/by/4.0/", "start": "2021-06-02", "applies_to": "vor" }, "references": [ { "key": "ref1", "unstructured": "Understanding Generative Adversarial Networks (GANs). (2019). Retrieved from https://towardsdatascience.com/understandinggenerative-adversarial-networks-gans-cd6e4651a29" }, { "key": "ref2", "unstructured": "Chollet, F. Deep learning with Python" }, { "key": "ref3", "unstructured": "Radford, A., Metz, L., &Chintala, S. (2016). Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. ICLR 2016" }, { "key": "ref4", "unstructured": "Denton, Emily, Chintala, Soumith, Szlam, Arthur, and Fergus, Rob. Deep generative image models using a laplacian pyramid of adversarial networks. arXiv preprint arXiv:1506.05751, 2015" }, { "key": "ref5", "doi": "10.1109/cvpr.2015.7298761", "unstructured": "Dosovitskiy, Alexey, Springenberg, Jost Tobias, and Brox, Thomas. Learning to generate chairs with convolutional neural networks. arXiv preprint arXiv:1411.5928, 2014" }, { "key": "ref6", "unstructured": "Danilo Jimenez Rezende, Shakir Mohamed, and DaanWierstra, “Stochastic Backpropagation and Approximate Inference in Deep Generative Models,” arXiv (2014)" }, { "key": "ref7", "unstructured": "Diederik P. Kingma and Max Welling, “Auto-Encoding Variational Bayes, arXiv (2013), https://arxiv.org/ abs/1312.6114" }, { "key": "ref8", "unstructured": "Bergstra, James and Bengio, Yoshua. Random search for hyper-parameter optimization. JMLR, 2012" }, { "key": "ref9", "doi": "10.1007/978-3-642-35289-8_30", "unstructured": "Coates, Adam and Ng, Andrew Y. Learning feature representations with k-means. In Neural Networks: Tricks of the Trade, pp. 561–580. Springer, 2012" }, { "key": "ref10", "unstructured": "Coates, Adam and Ng, Andrew. Selecting receptive fields in deep networks. NIPS, 2011" }, { "key": "ref11", "doi": "10.1109/cvpr.2009.5206848", "unstructured": "Deng, Jia, Dong, Wei, Socher, Richard, Li, Li-Jia, Li, Kai, and Fei-Fei, Li. Imagenet: A large-scale hierarchical image database. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pp. 248–255. IEEE, 2009" } ], "record": { "registrant": "Longman Publishers", "registered": "2026-09-12", "updated": "2026-09-20", "issue_number": 1, "source": "crossref-api", "source_agency": "Crossref (member 25296)" } }, "url_after": "https://www.jst.org.in/index.php/pub/article/view/854", "sha256_before": null, "sha256_after": "bee4b5eab62a3955f8eb2e214e7d6a030357e377e73e117223523ea5a40c50e6" }, { "seq": 2, "kind": "update", "at": "2026-09-30 00:00:01", "by": "Administrator (admin)", "by_kind": "user", "note": "record re-read from api.crossref.org", "changes": [ { "path": "container.titles.0.value", "from": "Journal of Science & Technology", "to": "Journal of Science & Technology" } ], "record_after": { "format": "smartscholars-doi-metadata/1.0", "doi": "10.46243/jst.2021.v6.i3.pp169-177", "referent": "Creation", "type": "JournalArticle", "structural_type": "Digital", "modes": [ "Visual" ], "characters": [ "Language" ], "titles": [ { "value": "Deep Convolutional Generative Adversial Network on MNIST Dataset", "type": "PrincipalTitle", "lang": "en" } ], "identifiers": [ { "type": "DOI", "value": "10.46243/jst.2021.v6.i3.pp169-177" } ], "agents": [ { "role": "author", "name": { "given": "S. Vijaya", "family": "Lakshmi" }, "sequence": "first" }, { "role": "author", "name": { "given": "Vallik Sai Ganesh", "family": "Raju Ganaraju" }, "sequence": "additional" }, { "role": "publisher", "name": { "org": "Longman Publishers" } } ], "dates": { "published": "2021-06-02", "date_type": "PublicationDate", "online": "2021-06-02" }, "language": "en", "container": { "type": "Journal", "titles": [ { "value": "Journal of Science & Technology", "type": "PrincipalTitle" } ], "identifiers": [ { "type": "ISSN", "value": "2456-5660", "medium": "electronic" } ], "volume": "06", "issue": "03", "pages": { "first": "169", "last": "177" } }, "links": [ { "url": "https://www.jst.org.in/index.php/pub/article/view/854", "return_type": "text/html", "primary": true }, { "url": "https://www.jst.org.in/index.php/pub/article/download/854/781", "purpose": "text-mining", "return_type": "application/pdf" }, { "url": "https://www.jst.org.in/index.php/pub/article/download/854/2432", "purpose": "text-mining", "return_type": "application/xml" }, { "url": "https://www.jst.org.in/index.php/pub/article/view/854/781", "purpose": "similarity-checking" } ], "abstract": { "value": "In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between the success of CNNs for supervised learning and unsupervised learning. We introduce a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrate that they are a strong candidate for unsupervised learning. Training on various image datasets, we show convincing evidence that our deep convolutional adversarial pair learns a hierarchy of representations from object parts to scenes in both the generator and discriminator. The generator uses tf.keras.layers.conv2Dtranspose (up sampling) layers to produce an image from a seed (random noise). Start with a dense layer that takes this seed as input, then up sample several times until you reach the desired image size of 28x28x1. The discriminator is a CNN-based image classifier. The model will be trained to output positive values for real images, and negative values for fake images. We define the Generator loss and the discriminator loss and we finally we get new images that look similar to our input(MNIST) images.", "lang": "en" }, "license": { "url": "https://creativecommons.org/licenses/by/4.0/", "start": "2021-06-02", "applies_to": "vor" }, "references": [ { "key": "ref1", "unstructured": "Understanding Generative Adversarial Networks (GANs). (2019). Retrieved from https://towardsdatascience.com/understandinggenerative-adversarial-networks-gans-cd6e4651a29" }, { "key": "ref2", "unstructured": "Chollet, F. Deep learning with Python" }, { "key": "ref3", "unstructured": "Radford, A., Metz, L., &Chintala, S. (2016). Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. ICLR 2016" }, { "key": "ref4", "unstructured": "Denton, Emily, Chintala, Soumith, Szlam, Arthur, and Fergus, Rob. Deep generative image models using a laplacian pyramid of adversarial networks. arXiv preprint arXiv:1506.05751, 2015" }, { "key": "ref5", "doi": "10.1109/cvpr.2015.7298761", "unstructured": "Dosovitskiy, Alexey, Springenberg, Jost Tobias, and Brox, Thomas. Learning to generate chairs with convolutional neural networks. arXiv preprint arXiv:1411.5928, 2014" }, { "key": "ref6", "unstructured": "Danilo Jimenez Rezende, Shakir Mohamed, and DaanWierstra, “Stochastic Backpropagation and Approximate Inference in Deep Generative Models,” arXiv (2014)" }, { "key": "ref7", "unstructured": "Diederik P. Kingma and Max Welling, “Auto-Encoding Variational Bayes, arXiv (2013), https://arxiv.org/ abs/1312.6114" }, { "key": "ref8", "unstructured": "Bergstra, James and Bengio, Yoshua. Random search for hyper-parameter optimization. JMLR, 2012" }, { "key": "ref9", "doi": "10.1007/978-3-642-35289-8_30", "unstructured": "Coates, Adam and Ng, Andrew Y. Learning feature representations with k-means. In Neural Networks: Tricks of the Trade, pp. 561–580. Springer, 2012" }, { "key": "ref10", "unstructured": "Coates, Adam and Ng, Andrew. Selecting receptive fields in deep networks. NIPS, 2011" }, { "key": "ref11", "doi": "10.1109/cvpr.2009.5206848", "unstructured": "Deng, Jia, Dong, Wei, Socher, Richard, Li, Li-Jia, Li, Kai, and Fei-Fei, Li. Imagenet: A large-scale hierarchical image database. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pp. 248–255. IEEE, 2009" } ], "record": { "registrant": "Longman Publishers", "registered": "2026-09-12", "updated": "2026-09-20", "issue_number": 1, "source": "crossref-api", "source_agency": "Crossref (member 25296)" } }, "url_after": "https://www.jst.org.in/index.php/pub/article/view/854", "sha256_before": "bee4b5eab62a3955f8eb2e214e7d6a030357e377e73e117223523ea5a40c50e6", "sha256_after": "c9065cf8ea89c5f4df99848f7e42d477d098a8a5df8d990a9989f2fa3d763bef" } ] }