[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128724-en":3,"doc-seo-128724-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128724,1099523882182,"Eliana","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Breaking the Structure of Multilayer Perceptrons with Complex Topologies - Research","Recent advances in neural network architectures suggest that complex topologies can outperform conventional feedforward networks, yet prior studies on topology–performance relationships remain inconsistent. This work evaluates directed acyclic graph (DAG) based networks as models for intricate neuron interrelationships, proposing an efficient training algorithm and comparing results against multilayer perceptrons (MLPs). Experiments on synthetic datasets with varied difficulty and noise show complex graph driven networks achieve higher accuracy, especially under high difficulty, while examining theoretical motivations and trade-offs.","Breaking the Structure of Multilayer Perceptrons with Complex Topologies  \nTommaso Boccato 1 Matteo Ferrante 1 Andrea Duggento 1 Nicola Toschi 1 2  \nAbstract  \nRecent advances in neural network (NN) architectures have demonstrated that complex topologies possess the potential to surpass the performance of conventional feedforward networks. Nonetheless, previous studies investigating the relationship between network topology and model performance have yielded inconsistent results, complicating their applicability in contexts beyond those scrutinized. In this study, we examine the utility of directed acyclic graphs (DAGs) for modeling intricate relationships among neurons within NNs.  \nWe introduce a novel algorithm for the efficient training of DAG-based networks and assess their performance relative to multilayer perceptrons (MLPs) . Through experimentation on synthetic datasets featuring varying levels of difficulty and noise, we observe that complex networks founded on pertinent graphs outperform MLPs in terms of accuracy, particularly within high-difficulty scenarios. Additionally, we explore the theoretical underpinnings of these observations and explore the potential trade-offs associated with employing complex networks. Our research offers valuable insights into the capabilities and constraints of complex NN architectures, thus contributing to the ongoing pursuit of designing more potent and efficient deep learning models.  \n1. Introduction  \nModern neural architectures are widely believed to draw significant design inspiration from biological neuronal networks. The artificial neuron, the fundamental functional unit of neural networks (NNs), is based on the McCulloch-Pitts  \n1Department of Biomedicine and Prevention, University of Rome Tor Vergata, Rome, Italy 2A.A. Martinos Center for Biomedical Imaging and Harvard Medical School, Boston, USA. Correspondence to: Tommaso Boccato \u003Ctom[maso.boccato@uniroma2.it](maso.boccato@uniroma2.it) > .  \nProceedings of the 2 nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML) at the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. 2023. Copyright 2023 by the author(s) .  \nunit (Fitch, 1944), sharing conceptual similarities with its biological counterpart. Additionally, state-of-the-art convolutional NNs incorporate several operations directly inspired by the mammalian primary visual cortex, such as nonlinear transduction, divisive normalization, and maximum-based pooling of inputs. However, these architectures may be among the few examples where the evolutionary structural and functional properties of neuronal systems have been genuinely relevant for NN design. Indeed, the topology of biological connectomes has not yet been translated into deep learning model engineering.  \nDue to the ease of implementation and deployment, widelyused neural architectures predominantly feature a regular structure resembling a sequence of functional blocks (e.g., neuronal layers) . The underlying multipartite graph of a multilayer perceptron (MLP) is typically controlled by a few hyperparameters that define its basic topological properties: depth, width, and layer sizes. Only recently have computer vision engineers transitioned from chain-like structures (Simonyan & Zisserman, 2014) to more elaborate connectivity patterns (He et al., 2016 ; Huang et al., 2017 ; Xie et al., 2019a) (e.g., skip connections, complete graphs) . Nevertheless, biological neuronal networks display much richer and less templated wirings at both the micro-and macroscale (Fornito et al., 2013) . Considering synaptic connections between individual neurons, the C. elegans nematode features a hierarchical modular (Bassett et al., 2010) connectome, wherein hubs with high betweenness centrality are efficiently interconnected (Barthelemy, 2004 ; Towlson et al., 2013) . Moreover, the strength distribution of the adult Drosophila central brain closely follows a power law with an expo","cbCaitGlQdxP6hKD","https://ap.wps.com/l/cbCaitGlQdxP6hKD","pdf",4770172,3,1,12,"English","en",105,"# Introduction\n## Topology and biological inspiration\n## Related work on complex networks","[{\"question\":\"What problem does the study address?\",\"answer\":\"It examines how directed acyclic graph (DAG) based topology in neural networks relates to predictive performance compared with multilayer perceptrons (MLPs).\"},{\"question\":\"What is introduced in the paper?\",\"answer\":\"A novel algorithm for efficiently training DAG based networks is proposed, followed by performance evaluation against MLPs.\"},{\"question\":\"How do results vary with dataset difficulty and noise?\",\"answer\":\"Across synthetic datasets with different levels of difficulty and noise, complex graph based networks outperform MLPs in accuracy, particularly in high difficulty scenarios.\"}]","Breaking the Structure of Multilayer Perceptrons with Complex Topologies - Research | PDF",1786002876,30,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"breaking-the-structure-of-multilayer-perceptrons-with-complex-topologies-research","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/breaking-the-structure-of-multilayer-perceptrons-with-complex-topologies-research/128724/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-25","2026-08-06",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the study address?","Question",{"text":76,"@type":77},"It examines how directed acyclic graph (DAG) based topology in neural networks relates to predictive performance compared with multilayer perceptrons (MLPs).","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What is introduced in the paper?",{"text":81,"@type":77},"A novel algorithm for efficiently training DAG based networks is proposed, followed by performance evaluation against MLPs.",{"name":83,"@type":74,"acceptedAnswer":84},"How do results vary with dataset difficulty and noise?",{"text":85,"@type":77},"Across synthetic datasets with different levels of difficulty and noise, complex graph based networks outperform MLPs in accuracy, particularly in high difficulty scenarios.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":30,"slug":122},"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]