{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/an-analysis-of-the-connections-between-layers","title":"An Analysis of the Connections Between Layers of Deep Neural Networks","arxiv_id":"1306.0152","date":"2013-06-01","proceeding":null,"authors":["Eugenio Culurciello","Jonghoon Jin","Aysegul Dundar","Jordan Bates"],"abstract":"We present an analysis of different techniques for selecting the connection\nbe- tween layers of deep neural networks. Traditional deep neural networks use\nran- dom connection tables between layers to keep the number of connections\nsmall and tune to different image features. This kind of connection performs\nadequately in supervised deep networks because their values are refined during\nthe training. On the other hand, in unsupervised learning, one cannot rely on\nback-propagation techniques to learn the connections between layers. In this\nwork, we tested four different techniques for connecting the first layer of the\nnetwork to the second layer on the CIFAR and SVHN datasets and showed that the\naccuracy can be im- proved up to 3% depending on the technique used. We also\nshowed that learning the connections based on the co-occurrences of the\nfeatures does not confer an advantage over a random connection table in small\nnetworks. This work is helpful to improve the efficiency of connections between\nthe layers of unsupervised deep neural networks.","url_abs":"http://arxiv.org/abs/1306.0152v1","url_pdf":"http://arxiv.org/pdf/1306.0152v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"an-analysis-of-the-connections-between-layers","repo_url":"https://github.com/cchinchristopherj/Right-Whale-Unsupervised-Model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}