{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:58:37Z","timestamp":1760597917553},"reference-count":25,"publisher":"MIT Press","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2019,12]]},"abstract":"<jats:p>A recent Cell paper (Chang &amp; Tsao, 2017 ) reports an interesting discovery. For the face stimuli generated by a pretrained active appearance model (AAM), the responses of neurons in the areas of the primate brain that are responsible for face recognition exhibit a strong linear relationship with the shape variables and appearance variables of the AAM that generates the face stimuli. In this letter, we show that this behavior can be replicated by a deep generative model, the generator network, that assumes that the observed signals are generated by latent random variables via a top-down convolutional neural network. Specifically, we learn the generator network from the face images generated by a pretrained AAM model using a variational autoencoder, and we show that the inferred latent variables of the learned generator network have a strong linear relationship with the shape and appearance variables of the AAM model that generates the face images. Unlike the AAM model, which has an explicit shape model where the shape variables generate the control points or landmarks, the generator network has no such shape model and shape variables. Yet it can learn the shape knowledge in the sense that some of the latent variables of the learned generator network capture the shape variations in the face images generated by AAM.<\/jats:p>","DOI":"10.1162\/neco_a_01236","type":"journal-article","created":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T21:52:21Z","timestamp":1571176341000},"page":"2348-2367","source":"Crossref","is-referenced-by-count":3,"title":["Replicating Neuroscience Observations on ML\/MF and AM Face Patches by Deep Generative Model"],"prefix":"10.1162","volume":"31","author":[{"given":"Tian","family":"Han","sequence":"first","affiliation":[{"name":"Department of Statistics, University of California, Los Angeles, Los Angeles, CA 90095, U.S.A."}]},{"given":"Xianglei","family":"Xing","sequence":"additional","affiliation":[{"name":"College of Automation, Harbin Engineering University, Heilongjiang, China 150001"}]},{"given":"Jiawen","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Southern California, Los Angeles, CA 90089, U.S.A."}]},{"given":"Ying Nian","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of California, Los Angeles, Los Angeles, CA 90095, U.S.A."}]}],"member":"281","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2017.05.011"},{"key":"B3","first-page":"2172","volume-title":"Advances in neural information processing systems","volume":"29","author":"Chen X.","year":"2016"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1109\/34.927467"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-09749-7_6"},{"key":"B6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"Dempster A. P.","year":"1977","journal-title":"Journal of the Royal Statistical Society: B"},{"key":"B7","first-page":"1486","volume-title":"Advances in neural information processing systems","volume":"28","author":"Denton E. L.","year":"2015"},{"key":"B8","author":"Dinh L.","year":"2016","journal-title":"CoRR"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"B10","first-page":"2672","volume-title":"Advances in neural information processing systems","volume":"27","author":"Goodfellow I.","year":"2014"},{"key":"B11","author":"Han T.","year":"2017","journal-title":"Proceedings of the 31st AAAI Conference on Artificial Intelligence"},{"issue":"5","key":"B12","first-page":"6","volume":"2","author":"Higgins I.","year":"2017","journal-title":"ICLR"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1126\/science.7761831"},{"key":"B14","author":"Ioffe S.","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning"},{"key":"B15","author":"Kingma D.","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"B16","author":"Kingma D. P.","year":"2013","journal-title":"Auto-encoding variational Bayes"},{"key":"B17","author":"Kingma D. P.","year":"2014","journal-title":"ICLR"},{"key":"B18","first-page":"1718","author":"Li Y.","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning"},{"key":"B19","first-page":"2924","volume-title":"Advances in neural information processing systems","volume":"27","author":"Montufar G. F.","year":"2014"},{"key":"B20","first-page":"1747","author":"Oord A. V. d.","year":"2016","journal-title":"Proceedings of the 33rd International Conference on Machine Learning"},{"key":"B21","author":"Radford A.","year":"2016","journal-title":"ICLR"},{"key":"B22","first-page":"1278","author":"Rezende D. J.","year":"2014","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"B23","first-page":"1218","author":"Salimans T.","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1716341115"},{"key":"B25","first-page":"10354","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Xing X.","year":"2019"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/neco_a_01236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T01:47:23Z","timestamp":1721872043000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/31\/12\/2348-2367\/95609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":25,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["10.1162\/neco_a_01236"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_01236","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12]]}}}