{"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/sparsity-in-deep-neural-networks-an-empirical","title":"Sparsity in Deep Neural Networks - An Empirical Investigation with TensorQuant","arxiv_id":"1808.08784","date":"2018-08-27","proceeding":null,"authors":["Dominik Marek Loroch","Franz-Josef Pfreundt","Norbert Wehn","Janis Keuper"],"abstract":"Deep learning is finding its way into the embedded world with applications\nsuch as autonomous driving, smart sensors and aug- mented reality. However, the\ncomputation of deep neural networks is demanding in energy, compute power and\nmemory. Various approaches have been investigated to reduce the necessary\nresources, one of which is to leverage the sparsity occurring in deep neural\nnetworks due to the high levels of redundancy in the network parameters. It has\nbeen shown that sparsity can be promoted specifically and the achieved sparsity\ncan be very high. But in many cases the methods are evaluated on rather small\ntopologies. It is not clear if the results transfer onto deeper topologies. In\nthis paper, the TensorQuant toolbox has been extended to offer a platform to\ninvestigate sparsity, especially in deeper models. Several practical relevant\ntopologies for varying classification problem sizes are investigated to show\nthe differences in sparsity for activations, weights and gradients.","url_abs":"http://arxiv.org/abs/1808.08784v1","url_pdf":"http://arxiv.org/pdf/1808.08784v1.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":"sparsity-in-deep-neural-networks-an-empirical","repo_url":"https://github.com/DominikFHG/TensorQuant","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"}],"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}