{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T03:51:47Z","timestamp":1773719507572,"version":"3.50.1"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T00:00:00Z","timestamp":1755129600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Reasoning and question answering, as fundamental cognitive functions in humans, remain significant hurdles for artificial intelligence. While large language models (LLMs) have achieved notable success, integrating explicit memory with structured reasoning capabilities remains a persistent difficulty. The Differentiable Neural Computer (DNC) model, despite addressing these issues to some extent, still faces challenges such as algorithmic complexity, slow convergence, and limited robustness. Inspired by the brain's learning and memory mechanisms, this paper proposes a Memory Transformation based Differentiable Neural Computer (MT-DNC) model. The MT-DNC integrates two brain-inspired memory modules\u2014a working memory module inspired by the cognitive system that temporarily holds and processes task-relevant information, and a long-term memory module that stores frequently accessed and enduring information\u2014within the DNC framework, enabling the autonomous transformation of acquired experiences between these memory systems. This facilitates efficient knowledge extraction and enhances reasoning capabilities. Experimental results on the bAbI question answering task demonstrate that the proposed method outperforms existing Deep Neural Network (DNN) and DNC models, achieving faster convergence and superior performance. Ablation studies further confirm that the transformation of memory from working memory to long-term memory is critical for improving the robustness and stability of reasoning. This work offers new insights into incorporating brain-inspired memory mechanisms into dialogue and reasoning systems.<\/jats:p>","DOI":"10.3389\/frai.2025.1635932","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T05:33:59Z","timestamp":1755149639000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A brain-inspired memory transformation based differentiable neural computer for reasoning-based question answering"],"prefix":"10.3389","volume":"8","author":[{"given":"Yao","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongjian","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feifei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.08774","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv:2303.08774"},{"key":"B2","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/S0079-7421(08)60422-3","article-title":"Human memory: a proposed system and its control processes","volume":"2","author":"Atkinson","year":"1968","journal-title":"Psychol. Learn. Motiv"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1610.06258","article-title":"Using fast weights to attend to the recent past","author":"Ba","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1607.06450","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint arXiv:1607.06450"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780198528012.001.0001","author":"Baddeley","year":"2007","journal-title":"Working Memory, Thought, and Action"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1809.02444","article-title":"Metamorphic relation based adversarial attacks on differentiable neural computer","author":"Chan","year":"2018","journal-title":"arXiv preprint arXiv:1809.02444"},{"key":"B7","article-title":"\u201cImproving differentiable neural computers through memory masking, de-allocation, and link distribution sharpness control,\u201d","volume-title":"International Conference on Learning Representations (ICLR)","author":"Csord\u00e1s","year":"2019"},{"key":"B8","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1146\/annurev-psych-113011-143750","article-title":"Executive functions","volume":"64","author":"Diamond","year":"2013","journal-title":"Annu. Rev. Psychol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.21783","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv:2407.21783"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-2606","article-title":"Robust and scalable differentiable neural computer for question answering","author":"Franke","year":"2018","journal-title":"arXiv preprint arXiv:1807.02658"},{"key":"B11","first-page":"1050","article-title":"\u201cDropout as a Bayesian approximation: representing model uncertainty in deep learning,\u201d","volume-title":"Proceedings of the 33rd ICML","author":"Gal","year":"2016"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1410.5401","article-title":"Neural turing machines","author":"Graves","year":"2014","journal-title":"arXiv preprint arXiv:1410.5401"},{"key":"B13","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1038\/nature20101","article-title":"Hybrid computing using a neural network with dynamic external memory","volume":"538","author":"Graves","year":"2016","journal-title":"Nature"},{"key":"B14","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.neuron.2017.06.011","article-title":"Neuroscience-inspired artificial intelligence","volume":"95","author":"Hassabis","year":"2017","journal-title":"Neuron"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1612.03969","article-title":"Tracking the world state with recurrent entity networks","author":"Henaff","year":"2016","journal-title":"arXiv preprint arXiv:1612.03969"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"B17","author":"Hsin","year":"2016","journal-title":"Implementation and Optimization of Differentiable Neural Computers"},{"key":"B18","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1038\/nn1825","article-title":"Coordinated memory replay in the visual cortex and hippocampus during sleep","volume":"10","author":"Ji","year":"2007","journal-title":"Nat. Neurosci"},{"key":"B19","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"B20","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1126\/science.aam6808","article-title":"Engrams and circuits crucial for systems consolidation of a memory","volume":"356","author":"Kitamura","year":"2017","journal-title":"Science"},{"key":"B21","article-title":"Self-normalizing neural networks","author":"Klambauer","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B22","first-page":"1378","article-title":"\u201cAsk me anything: dynamic memory networks for natural language processing,\u201d","volume-title":"International Conference on Machine Learning","author":"Kumar","year":"2016"},{"key":"B23","doi-asserted-by":"publisher","first-page":"e253","DOI":"10.1017\/S0140525X16001837","article-title":"Building machines that learn and think like people","volume":"40","author":"Lake","year":"2017","journal-title":"Behav. Brain Sci"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1901.01347","article-title":"Learning to remember more with less memorization","author":"Le","year":"2019","journal-title":"arXiv preprint arXiv:1901.01347"},{"key":"B25","first-page":"5682","article-title":"\u201cSelf-attentive associative memory,\u201d","volume-title":"International Conference on Machine Learning","author":"Le","year":"2020"},{"key":"B26","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1016\/S0896-6273(02)01096-6","article-title":"Memory of sequential experience in the hippocampus during slow wave sleep","volume":"36","author":"Lee","year":"2002","journal-title":"Neuron"},{"key":"B28","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1016\/j.tics.2007.09.001","article-title":"The contribution of sleep to hippocampus-dependent memory consolidation","volume":"11","author":"Marshall","year":"2007","journal-title":"Trends Cogn. Sci"},{"key":"B29","article-title":"Scaling memory-augmented neural networks with sparse reads and writes","author":"Rae","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B30","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1016\/j.neucom.2020.06.018","article-title":"EDNC: evolving differentiable neural computers","volume":"412","author":"Rasekh","year":"2020","journal-title":"Neurocomputing"},{"key":"B31","first-page":"1842","article-title":"\u201cMeta-learning with memory-augmented neural networks,\u201d","volume-title":"International Conference on Machine Learning","author":"Santoro","year":"2016"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1606.04582","article-title":"Query-reduction networks for question answering","author":"Seo","year":"2016","journal-title":"arXiv preprint arXiv:1606.04582"},{"key":"B33","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41524-021-00495-8","article-title":"Machine learning for perovskite materials design and discovery","volume":"7","author":"Tao","year":"2021","journal-title":"NPJ Comput. Mater"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.09288","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.05698","article-title":"Towards AI-complete question answering: a set of prerequisite toy tasks","author":"Weston","year":"2015","journal-title":"arXiv preprint arXiv:1502.05698"},{"key":"B37","doi-asserted-by":"publisher","first-page":"2339","DOI":"10.1016\/j.neuropsychologia.2010.04.016","article-title":"Memory formation and long-term retention in humans and animals: convergence towards a transformation account of hippocampal-neocortical interactions","volume":"48","author":"Winocur","year":"2010","journal-title":"Neuropsychologia"},{"key":"B38","first-page":"2397","article-title":"\u201cDynamic memory networks for visual and textual question answering,\u201d","volume-title":"International Conference on Machine Learning","author":"Xiong","year":"2016"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1505.00521","article-title":"Reinforcement learning neural turing machines-revised","author":"Zaremba","year":"2015","journal-title":"arXiv preprint arXiv:1505.00521"},{"key":"B40","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1049\/iet-its.2016.0208","article-title":"LSTM network: a deep learning approach for short-term traffic forecast","volume":"11","author":"Zhao","year":"2017","journal-title":"IET Intell. Transp. Syst"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1635932\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T05:34:02Z","timestamp":1755149642000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1635932\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,14]]},"references-count":40,"alternative-id":["10.3389\/frai.2025.1635932"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1635932","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,14]]},"article-number":"1635932"}}