{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/memory-semantization-through-perturbed-and","title":"Learning cortical representations through perturbed and adversarial dreaming","arxiv_id":"2109.04261","date":"2021-09-09","proceeding":null,"authors":["Nicolas Deperrois","Mihai A. Petrovici","Walter Senn","Jakob Jordan"],"abstract":"Humans and other animals learn to extract general concepts from sensory experience without extensive teaching. This ability is thought to be facilitated by offline states like sleep where previous experiences are systemically replayed. However, the characteristic creative nature of dreams suggests that learning semantic representations may go beyond merely replaying previous experiences. We support this hypothesis by implementing a cortical architecture inspired by generative adversarial networks (GANs). Learning in our model is organized across three different global brain states mimicking wakefulness, NREM and REM sleep, optimizing different, but complementary objective functions. We train the model on standard datasets of natural images and evaluate the quality of the learned representations. Our results suggest that generating new, virtual sensory inputs via adversarial dreaming during REM sleep is essential for extracting semantic concepts, while replaying episodic memories via perturbed dreaming during NREM sleep improves the robustness of latent representations. The model provides a new computational perspective on sleep states, memory replay and dreams and suggests a cortical implementation of GANs.","url_abs":"https://arxiv.org/abs/2109.04261v3","url_pdf":"https://arxiv.org/pdf/2109.04261v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"memory-semantization-through-perturbed-and","repo_url":"https://github.com/NicoZenith/PAD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"learning-semantic-representations","task_name":"Learning Semantic Representations"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dqn","method_name":"DQN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"q-learning","method_name":"Q-Learning"},{"method_slug":"rem","method_name":"REM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2109.04261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04261"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NicoZenith/PAD","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"144996bbf96e0763","entry":"get_indices","repo":"NicoZenith/PAD","repo_kind":"official","path":"fig6_compute_distances.py","file_url":"https://github.com/NicoZenith/PAD/blob/HEAD/fig6_compute_distances.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"144996bbf96e0763"}},{"code_sha256_prefix":"336eb7a33d8ba44f","entry":"grad_reverse","repo":"NicoZenith/PAD","repo_kind":"official","path":"network.py","file_url":"https://github.com/NicoZenith/PAD/blob/HEAD/network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"336eb7a33d8ba44f"}},{"code_sha256_prefix":"ea499c4c4345112d","entry":"mean_and_err","repo":"NicoZenith/PAD","repo_kind":"official","path":"fig5_plot_accuracies_occ.py","file_url":"https://github.com/NicoZenith/PAD/blob/HEAD/fig5_plot_accuracies_occ.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea499c4c4345112d"}},{"code_sha256_prefix":"3afc503597fcfe94","entry":"mean_and_sem","repo":"NicoZenith/PAD","repo_kind":"official","path":"fig4_plot_accuracies.py","file_url":"https://github.com/NicoZenith/PAD/blob/HEAD/fig4_plot_accuracies.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3afc503597fcfe94"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}