{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:07:02Z","timestamp":1753891622717,"version":"3.41.2"},"reference-count":11,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T00:00:00Z","timestamp":1676505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/V008242\/1"],"award-info":[{"award-number":["EP\/V008242\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neuroinform."],"abstract":"<jats:p>Latent representations are a necessary component of cognitive artificial intelligence (AI) systems. Here, we investigate the performance of various sequential clustering algorithms on latent representations generated by autoencoder and convolutional neural network (CNN) models. We also introduce a new algorithm, called Collage, which brings views and concepts into sequential clustering to bridge the gap with cognitive AI. The algorithm is designed to reduce memory requirements, numbers of operations (which translate into hardware clock cycles) and thus improve energy, speed and area performance of an accelerator for running said algorithm. Results show that plain autoencoders produce latent representations which have large inter-cluster overlaps. CNNs are shown to solve this problem, however introduce their own problems in the context of generalized cognitive pipelines.<\/jats:p>","DOI":"10.3389\/fninf.2023.1074653","type":"journal-article","created":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T12:37:30Z","timestamp":1676551050000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A study on the clusterability of latent representations in image pipelines"],"prefix":"10.3389","volume":"17","author":[{"given":"Adrian","family":"Wheeldon","sequence":"first","affiliation":[]},{"given":"Alexander","family":"Serb","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,2,16]]},"reference":[{"key":"B1","unstructured":"BlotM.\n          Study on Training Methods and Generalization Performance of Deep Learning for Image Classification2020"},{"key":"B2","article-title":"\u201cSteerable CNNs,\u201d","author":"Cohen","year":"2017","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2311","DOI":"10.1162\/neco_a_01331","article-title":"Resonator networks, 1: an efficient solution for factoring high-dimensional, distributed representations of data structures","volume":"32","author":"Frady","year":"2020","journal-title":"Neural Comput."},{"key":"B4","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/MCAS.2020.2988388","article-title":"Classification Using hyperdimensional computing: a review","volume":"20","author":"Ge","year":"2020","journal-title":"IEEE Circ. Syst. Mag."},{"journal-title":"Clustering Algorithms, 9th Edn.","year":"1975","author":"Hartigan","key":"B5"},{"key":"B6","doi-asserted-by":"crossref","first-page":"1591","DOI":"10.23919\/DATE.2019.8715147","article-title":"\u201cHDCluster: an accurate clustering using brain-inspired high-dimensional computing,\u201d","author":"Imani","year":"2019","journal-title":"2019 Design, Automation & Test in Europe Conference and Exhibition (DATE)"},{"journal-title":"Sparse Distributed Memory.","year":"1988","author":"Kanerva","key":"B7"},{"key":"B8","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc. IEEE"},{"key":"B9","article-title":"\u201cVector semantic representations as descriptors for visual place recognition,\u201d","author":"Neubert","year":"2021","journal-title":"Robotics: Science and Systems XVII"},{"key":"B10","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/s10851-019-00924-w","article-title":"Processing simple geometric attributes with autoencoders","volume":"62","author":"Newson","year":"2020","journal-title":"J. Math. Imaging Vis."},{"journal-title":"Pattern Recognition.","year":"2006","author":"Theodoridis","key":"B11"}],"container-title":["Frontiers in Neuroinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2023.1074653\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T12:37:38Z","timestamp":1676551058000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2023.1074653\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,16]]},"references-count":11,"alternative-id":["10.3389\/fninf.2023.1074653"],"URL":"https:\/\/doi.org\/10.3389\/fninf.2023.1074653","relation":{},"ISSN":["1662-5196"],"issn-type":[{"type":"electronic","value":"1662-5196"}],"subject":[],"published":{"date-parts":[[2023,2,16]]},"article-number":"1074653"}}