{"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/nerva-a-truly-sparse-implementation-of-neural","title":"Nerva: a Truly Sparse Implementation of Neural Networks","arxiv_id":"2407.17437","date":"2024-07-24","proceeding":null,"authors":["Wieger Wesselink","Bram Grooten","Qiao Xiao","Cassio de Campos","Mykola Pechenizkiy"],"abstract":"We introduce Nerva, a fast neural network library under development in C++. It supports sparsity by using the sparse matrix operations of Intel's Math Kernel Library (MKL), which eliminates the need for binary masks. We show that Nerva significantly decreases training time and memory usage while reaching equivalent accuracy to PyTorch. We run static sparse experiments with an MLP on CIFAR-10. On high sparsity levels like $99\\%$, the runtime is reduced by a factor of $4\\times$ compared to a PyTorch model using masks. Similar to other popular frameworks such as PyTorch and Keras, Nerva offers a Python interface for users to work with.","url_abs":"https://arxiv.org/abs/2407.17437v1","url_pdf":"https://arxiv.org/pdf/2407.17437v1.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":"nerva-a-truly-sparse-implementation-of-neural","repo_url":"https://github.com/wiegerw/nerva","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"math","task_name":"Math"}],"methods":[{"method_slug":null,"method_name":"Library"}],"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}