{"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/evaluating-the-performance-of-taaf-for-image","title":"Evaluating the Performance of TAAF for image classification models","arxiv_id":null,"date":"2025-02-13","proceeding":"- 2025 2","authors":["Bryn T Chatfield"],"abstract":"In this paper, we present the results of testing a custom activation function, The Analog Activation Function (TAAF), on both the MNIST and CIFAR-10 datasets. TAAF is a novel activation function designed to improve the performance of neural networks by leveraging a unique mathematical formulation. We evaluate TAAF in a convolutional neural network (CNN) architecture and compare its performance against standard activation functions on MNIST and against ELU on CIFAR-10. Our results demonstrate that TAAF achieves a test accuracy of 99.39% on the MNIST dataset and 79.37% on the CIFAR-10 dataset. On MNIST, TAAF achieves a slightly higher test accuracy of 99.39%, surpassing standard activation functions. On CIFAR-10, TAAF achieves a significantly higher test accuracy of 79.37% compared to ELU's 72.06% in the same architecture, suggesting improved generalization capabilities. This paper establishes a solid performance baseline for TAAF across different image classification tasks.","url_abs":"https://www.academia.edu/127610553/The_Analog_Activation_Function_TAAF_of_Emergent_Linear_Systems_Evaluating_the_Performance_of_The_Analog_Activation_Function_TAAF_on_MNIST_and_CIFAR_10_Datasets","url_pdf":"https://d1wqtxts1xzle7.cloudfront.net/121319618/Evaluating_the_Performance_of_TAAF_for_image_classification_models_6_.pdf?1739388413=&response-content-disposition=attachment%3B+filename%3DThe_Analog_Activation_Function_TAAF_of_E.pdf&Expires=1739392986&Signature=eWEFpnQ6JUuIRh1Q699x8RYj0-z6N3UaIhej91vT8m6RG-8zEr81QKUTpkaghPlo~byRxHzguZ4qn9Uk~5g8l5s23Kk1AcbS77iSwdjPRevvZe1W7dmIf9RNB~ora--fsTO9jYHSWk7RRHhdcNeULaLUuh8SkQN9jAeDuU5mgDLdSy6uI8me1HVbYZJwU70th~ZSVR6MSfR8i1w7EAsMQNPdynml7wc0FFo1bszz9RQ5rEqHhDoRXuCGwOeAlmy4jWp~qihf6gWG5797g2bXhJ9fHPa7796XWD12C9JZ0fFV-RYOGkSHweoPgah~uJ7I3D0v4EnGaTeZrbU8xHbrBA__&Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA","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":"evaluating-the-performance-of-taaf-for-image","repo_url":"https://github.com/bryn-gnolbs/TAAF-for-Image-Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"elu","method_name":"ELU"},{"method_slug":"taaf","method_name":"TAAF"}],"datasets_introduced":[],"methods_introduced":[{"slug":"taaf","name":"TAAF","full_name":"The Analog Activation Function"}],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"The Analog Activation Function","rank_in_archive_order":244,"of":265,"metrics":{"Cross Entropy Loss":"0.5551","Parameters":"545100","Percentage correct":"82.06","Top 1 Accuracy":"82.06"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"TAAF-CNN","rank_in_archive_order":31,"of":81,"metrics":{"Accuracy":"99.52%","Cross Entropy Loss":"0.0188","Epochs":"35","Percentage error":"0.48%","Trainable Parameters":"421642"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}