{"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/andhra-bandersnatch-training-neural-networks","title":"ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities","arxiv_id":"2411.19213","date":"2024-11-28","proceeding":null,"authors":["Venkata Satya Sai Ajay Daliparthi"],"abstract":"Inspired by the Many-Worlds Interpretation (MWI), this work introduces a novel neural network architecture that splits the same input signal into parallel branches at each layer, utilizing a Hyper Rectified Activation, referred to as ANDHRA. The branched layers do not merge and form separate network paths, leading to multiple network heads for output prediction. For a network with a branching factor of 2 at three levels, the total number of heads is 2^3 = 8 . The individual heads are jointly trained by combining their respective loss values. However, the proposed architecture requires additional parameters and memory during training due to the additional branches. During inference, the experimental results on CIFAR-10/100 demonstrate that there exists one individual head that outperforms the baseline accuracy, achieving statistically significant improvement with equal parameters and computational cost.","url_abs":"https://arxiv.org/abs/2411.19213v1","url_pdf":"https://arxiv.org/pdf/2411.19213v1.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":"andhra-bandersnatch-training-neural-networks","repo_url":"https://github.com/dvssajay/New_World","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"abnet","method_name":"ABNet"},{"method_slug":"andhra","method_name":"ANDHRA Module"}],"datasets_introduced":[],"methods_introduced":[{"slug":"abnet","name":"ABNet","full_name":"ANDHRA Bandersnatch Network"},{"slug":"andhra","name":"ANDHRA Module","full_name":"Ajay N’ Daliparthi Hyper Rectified Activation"}],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ABNet-2G-R3-Combined","rank_in_archive_order":115,"of":265,"metrics":{"Percentage correct":"96.378"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ABNet-2G-R3","rank_in_archive_order":121,"of":265,"metrics":{"Percentage correct":"96.088"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ABNet-2G-R2","rank_in_archive_order":125,"of":265,"metrics":{"Percentage correct":"95.900"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ABNet-2G-R1","rank_in_archive_order":131,"of":265,"metrics":{"Percentage correct":"95.536"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ABNet-2G-R0","rank_in_archive_order":163,"of":265,"metrics":{"Percentage correct":"94.118"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"ABNet-2G-R3-Combined","rank_in_archive_order":97,"of":211,"metrics":{"Percentage correct":"82.784"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"ABNet-2G-R3","rank_in_archive_order":124,"of":211,"metrics":{"Percentage correct":"80.830"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"ABNet-2G-R2","rank_in_archive_order":128,"of":211,"metrics":{"Percentage correct":"80.354"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"ABNet-2G-R1","rank_in_archive_order":136,"of":211,"metrics":{"Percentage correct":"78.792"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"ABNet-2G-R0","rank_in_archive_order":160,"of":211,"metrics":{"Percentage correct":"73.930"},"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}