{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:44:20Z","timestamp":1743086660136,"version":"3.40.3"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031723315"},{"type":"electronic","value":"9783031723322"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-72332-2_23","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T15:04:02Z","timestamp":1726499042000},"page":"343-362","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-organising Neural Discrete Representation Learning \u00e0 la Kohonen"],"prefix":"10.1007","author":[{"given":"Kazuki","family":"Irie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R\u00f3bert","family":"Csord\u00e1s","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00fcrgen","family":"Schmidhuber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"unstructured":"Agustsson, E., et al.: Soft-to-hard vector quantization for end-to-end learning compressible representations. In: Proceedings of Advances in Neural Information Processing Systems (NIPS), pp. 1141\u20131151 (2017)","key":"23_CR1"},{"issue":"3","key":"23_CR2","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1007\/BF02460791","volume":"42","author":"SI Amari","year":"1980","unstructured":"Amari, S.I.: Topographic organization of nerve fields. Bull. Math. Biol. 42(3), 339\u2013364 (1980)","journal-title":"Bull. Math. Biol."},{"unstructured":"Baevski, A., Schneider, S., Auli, M.: vq-wav2vec: self-supervised learning of discrete speech representations. In: International Conference on Learning Representations (ICLR). Virtual only (2020)","key":"23_CR3"},{"unstructured":"Bengio, Y., L\u00e9onard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. Preprint arXiv:1308.3432 (2013)","key":"23_CR4"},{"doi-asserted-by":"crossref","unstructured":"Borsos, Z., et al.: AudioLM: a language modeling approach to audio generation. Preprint arXiv:2209.03143 (2022)","key":"23_CR5","DOI":"10.1109\/TASLP.2023.3288409"},{"issue":"4","key":"23_CR6","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1006\/csla.1999.0128","volume":"13","author":"SF Chen","year":"1999","unstructured":"Chen, S.F., Goodman, J.: An empirical study of smoothing techniques for language modeling. Comput. Speech Lang. 13(4), 359\u2013393 (1999)","journal-title":"Comput. Speech Lang."},{"doi-asserted-by":"crossref","unstructured":"Choi, Y., Uh, Y., Yoo, J., Ha, J.: StarGAN v2: diverse image synthesis for multiple domains. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8185\u20138194. Virtual only (2020)","key":"23_CR7","DOI":"10.1109\/CVPR42600.2020.00821"},{"doi-asserted-by":"crossref","unstructured":"Constantinescu, A.O., O\u20196Reilly, J.X., Behrens, T.E.: Organizing conceptual knowledge in humans with a gridlike code. Science 352(6292), 1464\u20131468 (2016)","key":"23_CR8","DOI":"10.1126\/science.aaf0941"},{"issue":"1","key":"23_CR9","first-page":"1","volume":"39","author":"M Cottrell","year":"2018","unstructured":"Cottrell, M., Olteanu, M., Rossi, F., Villa-Vialaneix, N.: Self-organizing maps, theory and applications. Revista de Investigacion Operacional 39(1), 1\u201322 (2018)","journal-title":"Revista de Investigacion Operacional"},{"doi-asserted-by":"crossref","unstructured":"Csord\u00e1s, R., Irie, K., Schmidhuber, J.: CTL++: Evaluating generalization on never-seen compositional patterns of known functions, and compatibility of neural representations. In: Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP), Abu Dhabi, UAE (2022)","key":"23_CR10","DOI":"10.18653\/v1\/2022.emnlp-main.662"},{"key":"23_CR11","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.neucom.2003.09.009","volume":"56","author":"E De Bodt","year":"2004","unstructured":"De Bodt, E., Cottrell, M., Letremy, P., Verleysen, M.: On the use of self-organizing maps to accelerate vector quantization. Neurocomputing 56, 187\u2013203 (2004)","journal-title":"Neurocomputing"},{"doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, Florida, USA, pp. 248\u2013255 (2009)","key":"23_CR12","DOI":"10.1109\/CVPR.2009.5206848"},{"unstructured":"Dhariwal, P., Jun, H., Payne, C., Kim, J.W., Radford, A., Sutskever, I.: Jukebox: a generative model for music. Preprint arXiv:2005.00341 (2020)","key":"23_CR13"},{"doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12873\u201312883. Virtual only (2021)","key":"23_CR14","DOI":"10.1109\/CVPR46437.2021.01268"},{"unstructured":"Fortuin, V., H\u00fcser, M., Locatello, F., Strathmann, H., R\u00e4tsch, G.: SOM-VAE: interpretable discrete representation learning on time series. In: International Conference on Learning Representations (ICLR), New Orleans, LA, USA (May 2019)","key":"23_CR15"},{"unstructured":"Fritzke, B.: A growing neural gas network learns topologies. In: Proceedings of Advances in Neural Information Processing Systems (NIPS), Denver, CO, USA, pp. 625\u2013632 (1994)","key":"23_CR16"},{"key":"23_CR17","first-page":"78","volume":"62","author":"DO Hebb","year":"1949","unstructured":"Hebb, D.O.: The organization of behavior; a neuropsycholocigal theory. Wiley Book Clin. Psychol. 62, 78 (1949)","journal-title":"Wiley Book Clin. Psychol."},{"unstructured":"Hinton, G.: Neural networks for machine learning. Coursera, video lectures (2012)","key":"23_CR18"},{"unstructured":"Hu, W., Miyato, T., Tokui, S., Matsumoto, E., Sugiyama, M.: Learning discrete representations via information maximizing self-augmented training. In: Proceedings of International Conference on Machine Learning (ICML), Sydney, Australia, pp. 1558\u20131567 (2017)","key":"23_CR19"},{"unstructured":"Hupkes, D., Singh, A., Korrel, K., Kruszewski, G., Bruni, E.: Learning compositionally through attentive guidance. In: Proceedings of International Conference on Computational Linguistics and Intelligent Text Processing, La Rochelle, France (2019)","key":"23_CR20"},{"unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. In: International Conference on Learning Representations (ICLR), Toulon, France (2017)","key":"23_CR21"},{"unstructured":"Kaiser, L., Bengio, S., Roy, A., Vaswani, A., Parmar, N., Uszkoreit, J., Shazeer, N.: Fast decoding in sequence models using discrete latent variables. In: Proceedings of International Conference on Machine Learning (ICML), Stockholm, Sweden, pp. 2395\u20132404 (2018)","key":"23_CR22"},{"unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: Internatinal Conference on Learning Representations (ICLR), Vancouver, Canada (2018)","key":"23_CR23"},{"unstructured":"Keller, T.A., Welling, M.: Topographic vaes learn equivariant capsules. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), pp. 28585\u201328597. Virtual only (2021)","key":"23_CR24"},{"unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: International Conference on Learning Representations (ICLR), Banff, Canada (2014)","key":"23_CR25"},{"issue":"1","key":"23_CR26","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/BF00337288","volume":"43","author":"T Kohonen","year":"1982","unstructured":"Kohonen, T.: Self-organized formation of topologically correct feature maps. Biol. Cybern. 43(1), 59\u201369 (1982)","journal-title":"Biol. Cybern."},{"issue":"8","key":"23_CR27","doi-asserted-by":"publisher","first-page":"2081","DOI":"10.1162\/089976699300016098","volume":"11","author":"T Kohonen","year":"1999","unstructured":"Kohonen, T.: Comparison of SOM point densities based on different criteria. Neural Comput. 11(8), 2081\u20132095 (1999)","journal-title":"Neural Comput."},{"key":"23_CR28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-56927-2","volume-title":"Self-organizing Maps","author":"T Kohonen","year":"2001","unstructured":"Kohonen, T.: Self-organizing Maps. Springer, Heidelberg (2001). https:\/\/doi.org\/10.1007\/978-3-642-56927-2"},{"unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. Master\u2019s thesis, Computer Science Department, University of Toronto (2009)","key":"23_CR29"},{"doi-asserted-by":"crossref","unstructured":"Lee, D., Kim, C., Kim, S., Cho, M., Han, W.S.: Autoregressive image generation using residual quantization. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, pp. 11523\u201311532 (2022)","key":"23_CR30","DOI":"10.1109\/CVPR52688.2022.01123"},{"unstructured":"Liska, A., Kruszewski, G., Baroni, M.: Memorize or generalize? searching for a compositional RNN in a haystack. In: AEGAP Workshop ICML, Stockholm, Sweden (2018)","key":"23_CR31"},{"unstructured":"Liu, D., Niehues, J.: Learning an artificial language for knowledge-sharing in multilingual translation. In: Proceedings of Conference on Machine Translation (WMT), Abu Dhabi, pp. 188\u2013202 (2022)","key":"23_CR32"},{"unstructured":"Liu, D., et al.: Adaptive discrete communication bottlenecks with dynamic vector quantization. Preprint arXiv:2202.01334 (2022)","key":"23_CR33"},{"unstructured":"Liu, D., et al.: Discrete-valued neural communication. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), pp. 2109\u20132121. Virtual only (2021)","key":"23_CR34"},{"issue":"2","key":"23_CR35","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"S Lloyd","year":"1982","unstructured":"Lloyd, S.: Least squares quantization in PCM. IEEE Trans. Inf. Theory 28(2), 129\u2013137 (1982)","journal-title":"IEEE Trans. Inf. Theory"},{"unstructured":"MacQueen, J.: Classification and analysis of multivariate observations. In: Proceedings of Berkeley Symposium Mathematics Statistics Probability, pp. 281\u2013297 (1967)","key":"23_CR36"},{"issue":"2","key":"23_CR37","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/BF00288907","volume":"14","author":"C von der Malsburg","year":"1973","unstructured":"von der Malsburg, C.: Self-organization of orientation sensitive cells in the striate cortex. Kybernetik 14(2), 85\u2013100 (1973)","journal-title":"Kybernetik"},{"issue":"11","key":"23_CR38","doi-asserted-by":"publisher","first-page":"5176","DOI":"10.1073\/pnas.74.11.5176","volume":"74","author":"C von der Malsburg","year":"1977","unstructured":"von der Malsburg, C., Willshaw, D.J.: How to label nerve cells so that they can interconnect in an ordered fashion. Proc. Natl. Acad. Sci. 74(11), 5176\u20135178 (1977)","journal-title":"Proc. Natl. Acad. Sci."},{"doi-asserted-by":"crossref","unstructured":"Manduchi, L., H\u00fcser, M., Faltys, M., Vogt, J.E., R\u00e4tsch, G., Fortuin, V.: T-DPSOM: an interpretable clustering method for unsupervised learning of patient health states. In: Proceedings of Conference on Health, Inference, and Learning (CHIL), pp. 236\u2013245. Virtual only (2021)","key":"23_CR39","DOI":"10.1145\/3450439.3451872"},{"unstructured":"Martinetz, T., Schulten, K.: A \u201cneural-gas\u201d network learns topologies. In: Proceedings of International Conference on Artificial Neural Networks (ICANN), Espoo, Finland (1991)","key":"23_CR40"},{"doi-asserted-by":"crossref","unstructured":"Nasrabadi, N.M., Feng, Y.: Vector quantization of images based upon the Kohonen self-organizing feature maps. In: Proceedings of\u00a0IEEE International Conference on Neural Networks (ICNN), vol.\u00a01, pp. 101\u2013105 (1988)","key":"23_CR41","DOI":"10.1109\/ICNN.1988.23837"},{"issue":"3","key":"23_CR42","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/BF00275687","volume":"15","author":"E Oja","year":"1982","unstructured":"Oja, E.: Simplified neuron model as a principal component analyzer. J. Math. Biol. 15(3), 267\u2013273 (1982)","journal-title":"J. Math. Biol."},{"unstructured":"van\u00a0den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: Proc. Advances in Neural Information Processing Systems (NIPS), Long Beach, CA, pp. 6306\u20136315 (2017)","key":"23_CR43"},{"unstructured":"Ozair, S., Li, Y., Razavi, A., Antonoglou, I., van\u00a0den Oord, A., Vinyals, O.: Vector quantized models for planning. In: Proceedings of International Conference on Machine Learning (ICML), pp. 8302\u20138313. Virtual only (2021)","key":"23_CR44"},{"unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: Proceedings of International Conference on Machine Learning (ICML), vol.\u00a0139, pp. 8821\u20138831. Virtual only (2021)","key":"23_CR45"},{"unstructured":"Razavi, A., van\u00a0den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), Vancouver, Canada, pp. 14837\u201314847 (2019)","key":"23_CR46"},{"doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, pp. 10674\u201310685 (2022)","key":"23_CR47","DOI":"10.1109\/CVPR52688.2022.01042"},{"unstructured":"Roy, A., Vaswani, A., Parmar, N., Neelakantan, A.: Towards a better understanding of vector quantized autoencoders. OpenReview (2018)","key":"23_CR48"},{"unstructured":"Schlag, I., Irie, K., Schmidhuber, J.: Linear Transformers are secretly fast weight programmers. In: Proceedings of International Conference on Machine Learning (ICML). Virtual only (2021)","key":"23_CR49"},{"unstructured":"Schmidhuber, J.: Learning to control fast-weight memories: an alternative to recurrent nets. Technical Report. FKI-147-91, Institut f\u00fcr Informatik, Technische Universit\u00e4t M\u00fcnchen (March 1991)","key":"23_CR50"},{"doi-asserted-by":"crossref","unstructured":"Tirunagari, S., Bull, S., Kouchaki, S., Cooke, D., Poh, N.: Visualisation of survey responses using self-organising maps: a case study on diabetes self-care factors. In: Proceedings of\u00a0IEEE Symposium Series on Computational Intelligence (SSCI), pp.\u00a01\u20136 (2016)","key":"23_CR51","DOI":"10.1109\/SSCI.2016.7849896"},{"doi-asserted-by":"crossref","unstructured":"Tjandra, A., Sakti, S., Nakamura, S.: Transformer VQ-VAE for unsupervised unit discovery and speech synthesis: zerospeech 2020 challenge. In: Proceedings of Interspeech, pp. 4851\u20134855. Virtual only (2020)","key":"23_CR52","DOI":"10.21437\/Interspeech.2020-3033"},{"unstructured":"Tr\u00e4uble, F., et al.: Discrete key-value bottleneck. Preprint arXiv:2207.11240 (2022)","key":"23_CR53"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of Advances in Neural Information Processing Systems (NIPS), Long Beach, CA, USA, pp. 5998\u20136008 (2017)","key":"23_CR54"},{"unstructured":"Walker, J., Razavi, A., Oord, A.V.d.: Predicting video with VQVAE. Preprint arXiv:2103.01950 (2021)","key":"23_CR55"},{"doi-asserted-by":"crossref","unstructured":"Willshaw, D.J., von\u00a0der Malsburg, C.: How patterned neural connections can be set up by self-organization. Proc. Roy. Soc. Lond. Seri. B. Biol. Scie. 194(1117), 431\u2013445 (1976)","key":"23_CR56","DOI":"10.1098\/rspb.1976.0087"},{"doi-asserted-by":"crossref","unstructured":"Willshaw, D.J., von\u00a0der Malsburg, C.: A marker induction mechanism for the establishment of ordered neural mappings: its application to the retinotectal problem. Phil. Trans. Roy. Soc. Lond. B, Biol. Sci. 287(1021), 203\u2013243 (1979)","key":"23_CR57","DOI":"10.1098\/rstb.1979.0056"},{"unstructured":"Yan, W., Zhang, Y., Abbeel, P., Srinivas, A.: VideoGPT: video generation using vq-vae and transformers. Preprint arXiv:2104.10157 (2021)","key":"23_CR58"},{"doi-asserted-by":"crossref","unstructured":"Yin, H.: The self-organizing maps: background, theories, extensions and applications. In: Computational Intelligence: A Compendium, pp. 715\u2013762 (2008)","key":"23_CR59","DOI":"10.1007\/978-3-540-78293-3_17"},{"unstructured":"Yu, J., et al.: Vector-quantized image modeling with improved VQGAN. In: International Conference on Learning Representations (ICLR). Virtual only (2022)","key":"23_CR60"},{"unstructured":"Yu, J., et\u00a0al.: Scaling autoregressive models for content-rich text-to-image generation. Preprint arXiv:2206.10789 (2022)","key":"23_CR61"},{"key":"23_CR62","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1109\/TASLP.2021.3129994","volume":"30","author":"N Zeghidour","year":"2021","unstructured":"Zeghidour, N., Luebs, A., Omran, A., Skoglund, J., Tagliasacchi, M.: Soundstream: an end-to-end neural audio codec. IEEE\/ACM Trans. Audio Speech Lang. Process. 30, 495\u2013507 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72332-2_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T15:17:31Z","timestamp":1726499851000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72332-2_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723315","9783031723322"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72332-2_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}