{"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/optimizing-neural-network-hyperparameters","title":"Optimizing Neural Network Hyperparameters with Gaussian Processes for Dialog Act Classification","arxiv_id":"1609.08703","date":"2016-09-27","proceeding":null,"authors":["Franck Dernoncourt","Ji Young Lee"],"abstract":"Systems based on artificial neural networks (ANNs) have achieved\nstate-of-the-art results in many natural language processing tasks. Although\nANNs do not require manually engineered features, ANNs have many\nhyperparameters to be optimized. The choice of hyperparameters significantly\nimpacts models' performances. However, the ANN hyperparameters are typically\nchosen by manual, grid, or random search, which either requires expert\nexperiences or is computationally expensive. Recent approaches based on\nBayesian optimization using Gaussian processes (GPs) is a more systematic way\nto automatically pinpoint optimal or near-optimal machine learning\nhyperparameters. Using a previously published ANN model yielding\nstate-of-the-art results for dialog act classification, we demonstrate that\noptimizing hyperparameters using GP further improves the results, and reduces\nthe computational time by a factor of 4 compared to a random search. Therefore\nit is a useful technique for tuning ANN models to yield the best performances\nfor natural language processing tasks.","url_abs":"http://arxiv.org/abs/1609.08703v1","url_pdf":"http://arxiv.org/pdf/1609.08703v1.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":"optimizing-neural-network-hyperparameters","repo_url":"https://github.com/Franck-Dernoncourt/slt2016","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"},{"task_slug":"dialog-act-classification","task_name":"Dialog Act Classification"},{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"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}