{"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/introspection-accelerating-neural-network","title":"Introspection: Accelerating Neural Network Training By Learning Weight Evolution","arxiv_id":"1704.04959","date":"2017-04-17","proceeding":null,"authors":["Abhishek Sinha","Mausoom Sarkar","Aahitagni Mukherjee","Balaji Krishnamurthy"],"abstract":"Neural Networks are function approximators that have achieved\nstate-of-the-art accuracy in numerous machine learning tasks. In spite of their\ngreat success in terms of accuracy, their large training time makes it\ndifficult to use them for various tasks. In this paper, we explore the idea of\nlearning weight evolution pattern from a simple network for accelerating\ntraining of novel neural networks. We use a neural network to learn the\ntraining pattern from MNIST classification and utilize it to accelerate\ntraining of neural networks used for CIFAR-10 and ImageNet classification. Our\nmethod has a low memory footprint and is computationally efficient. This method\ncan also be used with other optimizers to give faster convergence. The results\nindicate a general trend in the weight evolution during training of neural\nnetworks.","url_abs":"http://arxiv.org/abs/1704.04959v1","url_pdf":"http://arxiv.org/pdf/1704.04959v1.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":"introspection-accelerating-neural-network","repo_url":"https://github.com/muneebshahid/introspection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}