{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:30:29Z","timestamp":1753893029806,"version":"3.41.2"},"reference-count":89,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T00:00:00Z","timestamp":1673395200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010755","name":"Instituto Nacional de Ci\u00eancia e Tecnologia de Informa\u00e7\u00e3o Qu\u00e2ntica","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010755","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Reversibility in artificial neural networks allows us to retrieve the input given an output. We present feature alignment, a method for approximating reversibility in arbitrary neural networks. We train a network by minimizing the distance between the output of a data point and the random output with respect to a random input. We applied the technique to the MNIST, CIFAR-10, CelebA, and STL-10 image datasets. We demonstrate that this method can roughly recover images from just their latent representation without the need of a decoder. By utilizing the formulation of variational autoencoders, we demonstrate that it is possible to produce new images that are statistically comparable to the training data. Furthermore, we demonstrate that the quality of the images can be improved by coupling a generator and a discriminator together. In addition, we show how this method, with a few minor modifications, can be used to train networks locally, which has the potential to save computational memory resources.<\/jats:p>","DOI":"10.3389\/frai.2022.1025148","type":"journal-article","created":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T07:01:03Z","timestamp":1673420463000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Feature alignment as a generative process"],"prefix":"10.3389","volume":"5","author":[{"given":"Tiago de Souza","family":"Farias","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonas","family":"Maziero","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,1,11]]},"reference":[{"key":"B1","first-page":"215","article-title":"An analysis of single layer networks in unsupervised feature learning,","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, Vol 15","author":"Adam","year":"2011"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1808.04730","article-title":"Analyzing inverse problems with invertible neural networks","author":"Ardizzone","year":"2019","journal-title":"arXiv:1808.04730 [cs, stat"},{"key":"B3","article-title":"Wasserstein GAN","author":"Arjovsky","year":"2017","journal-title":"arXiv:1701.07875 [cs, stat"},{"key":"B4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IJCNN.2019.8852449","article-title":"Improving the realism of synthetic images through a combination of adversarial and perceptual losses,","volume-title":"2019 International Joint Conference on Neural Networks (IJCNN)","author":"Atapattu","year":"2019"},{"key":"B5","doi-asserted-by":"crossref","first-page":"966","DOI":"10.1109\/IJCNN.2005.1555983","article-title":"One-step neural network inversion with PDF learning and emulation,","volume-title":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005, Vol. 2","author":"Baird","year":"2005"},{"key":"B6","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.neunet.2016.07.006","article-title":"A theory of local learning, the learning channel, and the optimality of backpropagation","volume":"83","author":"Baldi","year":"2016","journal-title":"Neural Netw"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1811.00995","article-title":"Invertible residual networks","author":"Behrmann","year":"2019","journal-title":"arXiv:1811.00995 [cs, stat"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1407.7906","article-title":"How auto-encoders could provide credit assignment in deep networks via target propagation","author":"Bengio","year":"2014","journal-title":"arXiv:1407.7906 [cs"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.03599","article-title":"Understanding disentangling in \u03b2-VAE","author":"Burgess","year":"2018","journal-title":"arXiv:1804.03599 [cs, stat"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1604.06174","article-title":"Training deep nets with sublinear memory cost","author":"Chen","year":"2016","journal-title":"arXiv:1604.06174"},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.1007\/11758549_78","article-title":"The data-flow equations of checkpointing in reverse automatic differentiation,","volume-title":"Computational Science 96 ICCS 2006. ICCS 2006. Lecture Notes in Computer Science, vol 3994","author":"Dauvergne","year":"2006"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1606.05908","article-title":"Tutorial on variational autoencoders","author":"Doersch","year":"2021","journal-title":"arXiv:1606.05908 [cs, stat"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1605.09782","article-title":"Adversarial feature learning","author":"Donahue","year":"2017","journal-title":"arXiv:1605.09782 [cs, stat"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.06304","article-title":"Deep neural networks are surprisingly reversible: a baseline for zero-shot inversion","author":"Dong","year":"2021","journal-title":"Techn. Rep"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1602.02644","article-title":"Generating images with perceptual similarity metrics based on deep networks","author":"Dosovitskiy","year":"2016","journal-title":"arXiv:1602.02644 [cs"},{"key":"B16","doi-asserted-by":"crossref","first-page":"3358","DOI":"10.1109\/BIBM52615.2021.9669593","article-title":"A novel activation maximization-based approach for insight into electrophysiology classifiers,","volume-title":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Ellis","year":"2021"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1109\/TRPMS.2021.3066428","article-title":"On interpretability of artificial neural networks: a survey","author":"Fan","year":"2021","journal-title":"arXiv:2001.02522 [cs, stat"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.09284","article-title":"Gradient target propagation","author":"Farias","year":"2018","journal-title":"arXiv:1810.09284 [cs"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2012.08795","article-title":"Study on the large batch size training of neural networks based on the second order gradient","author":"Gao","year":"2020","journal-title":"arXiv:2012.08795 [cs"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2018.00018","article-title":"Explaining explanations: an overview of interpretability of machine learning","author":"Gilpin","year":"2019","journal-title":"arXiv:1806.00069 [cs, stat"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1707.04585","article-title":"The reversible residual network: backpropagation without storing activations","author":"Gomez","year":"2017","journal-title":"arXiv:1707.04585 [cs"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.2661","article-title":"Generative adversarial networks","author":"Goodfellow","year":"2014","journal-title":"arXiv:1406.2661 [cs, stat"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.01367","article-title":"FFJORD: free-form continuous dynamics for scalable reversible generative models","author":"Grathwohl","year":"2018","journal-title":"arXiv:1810.01367 [cs, stat"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2001.06937","article-title":"A review on generative adversarial networks: algorithms, theory, and applications","author":"Gui","year":"2020","journal-title":"arXiv:2001.06937 [cs, stat"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.07141","article-title":"BackLink: supervised local training with backward links","author":"Guo","year":"2022","journal-title":"Techn. Rep"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.14758","article-title":"Preventing posterior collapse with levenshtein variational autoencoder","author":"Havrylov","year":"2020","journal-title":"arXiv:2004.14758 [cs, stat"},{"key":"B27","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition,","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He","year":"2016"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/S0361-9230(99)00182-3","article-title":"The organization of behavior","author":"Hebb","year":"1949","journal-title":"Wiley Brain Res. Bull"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.08500","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2018","journal-title":"arXiv:1706.08500 [cs, stat"},{"key":"B30","article-title":"beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework,","author":"Higgins","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"B31","first-page":"6840","article-title":"Denoising diffusion probabilistic models,","volume-title":"Advances in Neural Information Processing Systems, Vol. 33","author":"Ho","year":"2020"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2001.05992","article-title":"Provable Benefit of orthogonal initialization in optimizing deep linear networks","author":"Hu","year":"2020","journal-title":"arXiv:2001.05992 [cs, math, stat"},{"key":"B33","article-title":"Improving deep learning interpretability by saliency guided training,","volume-title":"Advances in Neural Information Processing Systems","author":"Ismail","year":"2021"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1038\/srep28073","article-title":"A local learning rule for independent component analysis","author":"Isomura","year":"2016","journal-title":"Sci. Rep"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-20082-0","article-title":"Error-gated hebbian rule: a local learning rule for principal and independent component analysis","author":"Isomura","year":"2018","journal-title":"Sci. Rep"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.03591","article-title":"A survey on neural network language models","author":"Jing","year":"2019","journal-title":"arXiv:1906.03591 [cs"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43","article-title":"Perceptual losses for real-time style transfer and super-resolution","author":"Johnson","year":"2016","journal-title":"arXiv:1603.08155 [cs]"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2017","journal-title":"arXiv:1412.6980 [cs"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1807.03039","article-title":"Glow: generative flow with invertible 1x1 convolutions","author":"Kingma","year":"2018","journal-title":"arXiv:1807.03039 [cs, stat"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014","journal-title":"arXiv:1312.6114 [cs, stat"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1561\/9781680836233","article-title":"An introduction to variational autoencoders","author":"Kingma","year":"2019","journal-title":"arXiv:1906.02691 [cs, stat"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1908.09257","article-title":"Normalizing flows: an introduction and review of current methods","author":"Kobyzev","year":"2020","journal-title":"arXiv:1908.09257 [cs, stat"},{"journal-title":"Learning Multiple Layers of Features From Tiny Images","year":"2009","author":"Krizhevsky","key":"B43"},{"key":"B44","article-title":"ImageNet classification with deep convolutional neural networks,","volume-title":"Advances in Neural Information Processing Systems, Vol. 25","author":"Krizhevsky","year":"2012"},{"key":"B45","doi-asserted-by":"publisher","first-page":"7723","DOI":"10.1073\/pnas.1820458116","article-title":"Unsupervised learning by competing hidden units","volume":"116","author":"Krotov","year":"2019","journal-title":"Proc. Natl. Acad. Sci. U.S.A"},{"key":"B46","article-title":"Efficient rematerialization for deep networks,","volume-title":"Advances in Neural Information Processing Systems, Vol. 32","author":"Kumar","year":"2019"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.09300","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"Larsen","year":"2016","journal-title":"arXiv:1512.09300 [cs, stat"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2012.03837","article-title":"Parallel training of deep networks with local updates","author":"Laskin","year":"2021","journal-title":"arXiv:2012.03837"},{"key":"B49","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":"B50","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1145\/2001269.2001295","article-title":"Unsupervised learning of hierarchical representations with convolutional deep belief networks","volume":"54","author":"Lee","year":"2011","journal-title":"Commun. ACM"},{"key":"B51","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1038\/s41583-020-0277-3","article-title":"Backpropagation and the brain","volume":"21","author":"Lillicrap","year":"2020","journal-title":"Nat. Rev. Neurosci"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.09549","article-title":"Learning to learn with feedback and local plasticity","author":"Lindsey","year":"2020","journal-title":"arXiv:2006.09549 [cs, q-bio"},{"key":"B53","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1007\/BF01931367","article-title":"Taylor expansion of the accumulated rounding error","volume":"16","author":"Linnainmaa","year":"1976","journal-title":"BIT Num. Math"},{"key":"B54","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2015.425","article-title":"Deep learning face attributes in the wild,","volume-title":"Proceedings of International Conference on Computer Vision (ICCV)","author":"Liu","year":"2015"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.02469","article-title":"Don't blame the ELBO! A linear VAE perspective on posterior collapse","author":"Lucas","year":"2019","journal-title":"arXiv:1911.02469 [cs, stat"},{"key":"B56","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/s11263-016-0911-8","article-title":"Visualizing deep convolutional neural networks using natural pre-images","volume":"120","author":"Mahendran","year":"2016","journal-title":"Int. J. Comput. Vis"},{"key":"B57","doi-asserted-by":"crossref","first-page":"2813","DOI":"10.1109\/ICCV.2017.304","article-title":"Least squares generative adversarial networks,","volume-title":"2017 IEEE International Conference on Computer Vision (ICCV)","author":"Mao","year":"2017"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2009.05359","article-title":"Activation relaxation: a local dynamical approximation to backpropagation in the brain","author":"Millidge","year":"2020","journal-title":"arXiv:2009.05359 [cs, q-bio"},{"key":"B59","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines,","author":"Nair","year":"2010","journal-title":"Proceedings of the 27th International Conference on International Conference on Machine Learning"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1605.09304","article-title":"Synthesizing the preferred inputs for neurons in neural networks via deep generator networks","author":"Nguyen","year":"","journal-title":"arXiv:1605.09304 [cs"},{"key":"B61","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1602.03616","article-title":"Multifaceted feature visualization: uncovering the different types of features learned by each neuron in deep neural networks","author":"Nguyen","year":"","journal-title":"arXiv:1602.03616 [cs"},{"key":"B62","doi-asserted-by":"publisher","first-page":"e7","DOI":"10.23915\/distill.00007","article-title":"Feature visualization","volume":"2","author":"Olah","year":"2017","journal-title":"Distill"},{"key":"B63","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1803.01834","article-title":"Conducting credit assignment by aligning local representations","author":"Ororbia","year":"2018","journal-title":"arXiv:1803.01834 [cs, stat"},{"key":"B64","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1910.13233","article-title":"Neural density estimation and likelihood-free inference","author":"Papamakarios","year":"2019","journal-title":"arXiv:1910.13233 [cs, stat"},{"key":"B65","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.00597","article-title":"Taming VAEs","author":"Rezende","year":"2018","journal-title":"arXiv:1810.00597 [cs, stat"},{"key":"B66","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01042","article-title":"High-resolution image synthesis with latent diffusion models,","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Rombach","year":"2022"},{"key":"B67","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: Convolutional networks for biomedical image segmentation,","volume-title":"Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015","author":"Ronneberger","year":"2015"},{"key":"B68","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"B69","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.13178","article-title":"Generative adversarial networks (GANs): an overview of theoretical model, evaluation metrics, and recent developments","author":"Salehi","year":"2020","journal-title":"arXiv:2005.13178 [cs, eess"},{"key":"B70","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.03725","article-title":"Predictive coding can do exact backpropagation on convolutional and recurrent neural networks","author":"Salvatori","year":"2021","journal-title":"arXiv:2103.03725 [cs"},{"key":"B71","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6120","article-title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","author":"Saxe","year":"2014","journal-title":"arXiv:1312.6120 [cond-mat, q-bio, stat"},{"key":"B72","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1806.01610","article-title":"Training generative reversible networks","author":"Schirrmeister","year":"2018","journal-title":"arXiv:1806.01610 [cs, stat"},{"key":"B73","article-title":"pytorch-fid: FID score for PyTorch","author":"Seitzer","year":"2020","journal-title":"Version 0.1.1"},{"key":"B74","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int. J. Comput. Vis"},{"key":"B75","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.01792","article-title":"A survey on understanding, visualizations, and explanation of deep neural networks","author":"Shahroudnejad","year":"2021","journal-title":"arXiv:2102.01792 [cs"},{"key":"B76","first-page":"9240","article-title":"Interpreting the latent space of gans for semantic face editing,","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Shen","year":"2020"},{"key":"B77","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF44664.2019.9048921","article-title":"A Closer look at disentangling in \u03b2-VAE","author":"Sikka","year":"2019","journal-title":"arXiv:1912.05127 [cs, stat"},{"key":"B78","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics,","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings of Machine Learning Research","author":"Sohl-Dickstein","year":"2015"},{"key":"B79","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1904.10631","article-title":"Low-memory neural network training: a technical report","author":"Sohoni","year":"2019","journal-title":"arXiv:1904.10631 [cs, stat"},{"key":"B80","first-page":"22566","article-title":"Can the brain do backpropagation? exact implementation of backpropagation in predictive coding networks","volume":"33","author":"Song","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B81","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6806","article-title":"Striving for simplicity: the all convolutional net","author":"Springenberg","year":"2015","journal-title":"arXiv:1412.6806 [cs"},{"key":"B82","doi-asserted-by":"crossref","first-page":"2818","DOI":"10.1109\/CVPR.2016.308","article-title":"Rethinking the inception architecture for computer vision,","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Szegedy","year":"2016"},{"key":"B83","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.08663","article-title":"Preventing posterior collapse induced by oversmoothing in gaussian VAE","author":"Takida","year":"2021","journal-title":"arXiv:2102.08663 [cs"},{"key":"B84","doi-asserted-by":"publisher","DOI":"10.3390\/jsan10030039","article-title":"A study of fall detection in assisted living: identifying and improving the optimal machine learning method","author":"Thakur","year":"2021","journal-title":"J. Sensor Actuator Netw"},{"key":"B85","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.3390\/electronics9091432","article-title":"Neural network for low-memory IoT devices and MNIST image recognition using kernels based on logistic map","volume":"9","author":"Velichko","year":"2020","journal-title":"Electronics"},{"key":"B86","article-title":"Revisiting locally supervised learning: an alternative to end-to-end training,","author":"Wang","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"B87","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/j.tics.2018.12.005","article-title":"Theories of error back-propagation in the brain","volume":"23","author":"Whittington","year":"2019","journal-title":"Trends Cogn. Sci"},{"key":"B88","article-title":"Large Batch training of convolutional networks","author":"You","year":"2017","journal-title":"arXiv:1708.03888 [cs"},{"key":"B89","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1708.03888","article-title":"A new method to visualize deep neural networks","author":"Zintgraf","year":"2017","journal-title":"arXiv:1603.02518 [cs"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2022.1025148\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T07:01:48Z","timestamp":1673420508000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2022.1025148\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,11]]},"references-count":89,"alternative-id":["10.3389\/frai.2022.1025148"],"URL":"https:\/\/doi.org\/10.3389\/frai.2022.1025148","relation":{},"ISSN":["2624-8212"],"issn-type":[{"type":"electronic","value":"2624-8212"}],"subject":[],"published":{"date-parts":[[2023,1,11]]},"article-number":"1025148"}}