{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T17:03:46Z","timestamp":1775581426698,"version":"3.50.1"},"reference-count":89,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100018693","name":"Horizon Europe","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1016\/j.neunet.2025.107794","type":"journal-article","created":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T02:51:21Z","timestamp":1751424681000},"page":"107794","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Embeddings hidden layers learning for neural network compression"],"prefix":"10.1016","volume":"191","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1611-966X","authenticated-orcid":false,"given":"Jia Cheng","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0166-0898","authenticated-orcid":false,"given":"Roberto","family":"Cavicchioli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8705-0761","authenticated-orcid":false,"given":"Alessandro","family":"Capotondi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.107794_b1","series-title":"SC22: international conference for high performance computing, networking, storage and analysis","first-page":"1","article-title":"DeepSpeed-inference: enabling efficient inference of transformer models at unprecedented scale","author":"Aminabadi","year":"2022"},{"key":"10.1016\/j.neunet.2025.107794_b2","series-title":"Computer vision\u2013ECCV 2016: 14th European conference, amsterdam, the netherlands, October 11-14, 2016, proceedings, part v 14","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"Anderson","year":"2016"},{"key":"10.1016\/j.neunet.2025.107794_b3","article-title":"Deep equilibrium models","volume":"32","author":"Bai","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107794_b4","series-title":"Binarybert: Pushing the limit of bert quantization","author":"Bai","year":"2020"},{"key":"10.1016\/j.neunet.2025.107794_b5","series-title":"ICC 2023-IEEE international conference on communications","first-page":"1706","article-title":"G-BERT: Enabling green BERT deployment on FPGA via hardware-aware hybrid pruning","author":"Bai","year":"2023"},{"key":"10.1016\/j.neunet.2025.107794_b6","unstructured":"Banerjee, S., & Lavie, A. (2005). METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization (pp. 65\u201372)."},{"key":"10.1016\/j.neunet.2025.107794_b7","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107794_b8","series-title":"Adabert: Task-adaptive bert compression with differentiable neural architecture search","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2025.107794_b9","series-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"10.1016\/j.neunet.2025.107794_b10","unstructured":"Dasgupta, S., & Cohn, T. (2025). Improving Language Model Distillation through Hidden State Matching. In The thirteenth international conference on learning representations."},{"key":"10.1016\/j.neunet.2025.107794_b11","series-title":"Universal transformers","author":"Dehghani","year":"2018"},{"key":"10.1016\/j.neunet.2025.107794_b12","article-title":"Predicting parameters in deep learning","volume":"26","author":"Denil","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107794_b13","series-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"10.1016\/j.neunet.2025.107794_b14","series-title":"VTrans: Accelerating transformer compression with variational information bottleneck based pruning","author":"Dutta","year":"2024"},{"key":"10.1016\/j.neunet.2025.107794_b15","doi-asserted-by":"crossref","unstructured":"Finkelstein, L., Gabrilovich, E., Matias, Y., Rivlin, E., Solan, Z., Wolfman, G., et al. (2001). Placing search in context: The concept revisited. In Proceedings of the 10th international conference on world wide web (pp. 406\u2013414).","DOI":"10.1145\/371920.372094"},{"key":"10.1016\/j.neunet.2025.107794_b16","series-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"Frankle","year":"2018"},{"key":"10.1016\/j.neunet.2025.107794_b17","series-title":"International conference on machine learning","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"Gehring","year":"2017"},{"key":"10.1016\/j.neunet.2025.107794_b18","series-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2015"},{"key":"10.1016\/j.neunet.2025.107794_b19","series-title":"Modeling recurrence for transformer","author":"Hao","year":"2019"},{"key":"10.1016\/j.neunet.2025.107794_b20","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., & Sun, J. (2017). Channel pruning for accelerating very deep neural networks. In Proceedings of the IEEE international conference on computer vision (pp. 1389\u20131397).","DOI":"10.1109\/ICCV.2017.155"},{"key":"10.1016\/j.neunet.2025.107794_b21","series-title":"Proceedings of the 5th international workshop on semantic evaluation","first-page":"33","article-title":"SemEval-2010 task 8: Multi-way classification of semantic relations between pairs of nominals","author":"Hendrickx","year":"2010"},{"key":"10.1016\/j.neunet.2025.107794_b22","series-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"issue":"8","key":"10.1016\/j.neunet.2025.107794_b23","doi-asserted-by":"crossref","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 Computation"},{"key":"10.1016\/j.neunet.2025.107794_b24","first-page":"18225","article-title":"Sharebert: Embeddings are capable of learning hidden layers","volume":"vol. 38","author":"Hu","year":"2024"},{"key":"10.1016\/j.neunet.2025.107794_b25","series-title":"2023 IEEE international conference on big data (bigData)","first-page":"2173","article-title":"Exploiting multiple sequence lengths in fast end to end training for image captioning","author":"Hu","year":"2023"},{"key":"10.1016\/j.neunet.2025.107794_b26","series-title":"International conference on image analysis and processing","first-page":"39","article-title":"A request for clarity over the end of sequence token in the self-critical sequence training","author":"Hu","year":"2023"},{"key":"10.1016\/j.neunet.2025.107794_b27","series-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"10.1016\/j.neunet.2025.107794_b28","doi-asserted-by":"crossref","unstructured":"Hu, Y., Zhang, J., Zhao, Z., Zhao, C., Chen, X., Li, C., et al. (2024). SP3: Enhancing Structured Pruning via PCA Projection. In Findings of the association for computational linguistics ACL 2024 (pp. 3150\u20133170).","DOI":"10.18653\/v1\/2024.findings-acl.187"},{"key":"10.1016\/j.neunet.2025.107794_b29","doi-asserted-by":"crossref","first-page":"2850","DOI":"10.1109\/TASLP.2023.3289303","article-title":"Uncertainty-driven knowledge distillation for language model compression","volume":"31","author":"Huang","year":"2023","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10.1016\/j.neunet.2025.107794_b30","doi-asserted-by":"crossref","unstructured":"Huang, Z., Hou, L., Shang, L., Jiang, X., Chen, X., & Liu, Q. (2021). Ghostbert: Generate more features with cheap operations for bert. In Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (volume 1: long papers) (pp. 6512\u20136523).","DOI":"10.18653\/v1\/2021.acl-long.509"},{"key":"10.1016\/j.neunet.2025.107794_b31","unstructured":"Huang, E. H., Socher, R., Manning, C. D., & Ng, A. Y. (2012). Improving word representations via global context and multiple word prototypes. In Proceedings of the 50th annual meeting of the association for computational linguistics (volume 1: long papers) (pp. 873\u2013882)."},{"key":"10.1016\/j.neunet.2025.107794_b32","series-title":"PC-LoRA: Low-rank adaptation for progressive model compression with knowledge distillation","author":"Hwang","year":"2024"},{"key":"10.1016\/j.neunet.2025.107794_b33","series-title":"How to train bert with an academic budget","author":"Izsak","year":"2021"},{"key":"10.1016\/j.neunet.2025.107794_b34","series-title":"Tinybert: Distilling bert for natural language understanding","author":"Jiao","year":"2019"},{"key":"10.1016\/j.neunet.2025.107794_b35","series-title":"Proceedings of the 2018 conference on empirical methods in natural language processing: system demonstrations","first-page":"66","article-title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for neural text processing","author":"Kudo","year":"2018"},{"key":"10.1016\/j.neunet.2025.107794_b36","doi-asserted-by":"crossref","unstructured":"Kurtic, E., Campos, D., Nguyen, T., Frantar, E., Kurtz, M., Fineran, B., et al. (2022). The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models. In Proceedings of the 2022 conference on empirical methods in natural language processing (pp. 4163\u20134181).","DOI":"10.18653\/v1\/2022.emnlp-main.279"},{"key":"10.1016\/j.neunet.2025.107794_b37","series-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2019"},{"key":"10.1016\/j.neunet.2025.107794_b38","series-title":"Fnet: Mixing tokens with fourier transforms","author":"Lee-Thorp","year":"2021"},{"key":"10.1016\/j.neunet.2025.107794_b39","series-title":"Homodistil: Homotopic task-agnostic distillation of pre-trained transformers","author":"Liang","year":"2023"},{"key":"10.1016\/j.neunet.2025.107794_b40","series-title":"PGB: One-shot pruning for BERT via weight grouping and permutation","author":"Lim","year":"2025"},{"key":"10.1016\/j.neunet.2025.107794_b41","series-title":"Text summarization branches out","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"issue":"3","key":"10.1016\/j.neunet.2025.107794_b42","doi-asserted-by":"crossref","DOI":"10.3390\/s23031483","article-title":"LAD: Layer-wise adaptive distillation for BERT model compression","volume":"23","author":"Lin","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.neunet.2025.107794_b43","series-title":"2018 Design, automation & test in europe conference & exhibition","first-page":"1045","article-title":"FFT-based deep learning deployment in embedded systems","author":"Lin","year":"2018"},{"key":"10.1016\/j.neunet.2025.107794_b44","series-title":"European conference on computer vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neunet.2025.107794_b45","first-page":"87","article-title":"AWQ: Activation-aware weight quantization for on-device LLM compression and acceleration","volume":"6","author":"Lin","year":"2024","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"10.1016\/j.neunet.2025.107794_b46","series-title":"On the variance of the adaptive learning rate and beyond","author":"Liu","year":"2019"},{"key":"10.1016\/j.neunet.2025.107794_b47","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., et al. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 10012\u201310022).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.neunet.2025.107794_b48","first-page":"8715","article-title":"Rosita: Refined bert compression with integrated techniques","volume":"vol. 35","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2025.107794_b49","series-title":"MobileLLM: Optimizing sub-billion parameter language models for on-device use cases","author":"Liu","year":"2024"},{"key":"10.1016\/j.neunet.2025.107794_b50","series-title":"Proceedings of the seventeenth conference on computational natural language learning","first-page":"104","article-title":"Better word representations with recursive neural networks for morphology","author":"Luong","year":"2013"},{"issue":"9","key":"10.1016\/j.neunet.2025.107794_b51","doi-asserted-by":"crossref","first-page":"2533","DOI":"10.3390\/s20092533","article-title":"Edge machine learning for ai-enabled iot devices: A review","volume":"20","author":"Merenda","year":"2020","journal-title":"Sensors"},{"key":"10.1016\/j.neunet.2025.107794_b52","series-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"10.1016\/j.neunet.2025.107794_b53","series-title":"GAP9shield: A 150gops AI-capable ultra-low power module for vision and ranging applications on nano-drones","author":"M\u00fcller","year":"2024"},{"key":"10.1016\/j.neunet.2025.107794_b54","doi-asserted-by":"crossref","first-page":"70528","DOI":"10.1109\/ACCESS.2018.2879615","article-title":"A review of low-end, middle-end, and high-end IoT devices","volume":"6","author":"Ojo","year":"2018","journal-title":"IEEE Access"},{"key":"10.1016\/j.neunet.2025.107794_b55","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., & Manning, C. D. (2014). Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (pp. 1532\u20131543).","DOI":"10.3115\/v1\/D14-1162"},{"key":"10.1016\/j.neunet.2025.107794_b56","series-title":"A call for clarity in reporting BLEU scores","author":"Post","year":"2018"},{"key":"10.1016\/j.neunet.2025.107794_b57","series-title":"Subformer: Exploring weight sharing for parameter efficiency in generative transformers","author":"Reid","year":"2021"},{"key":"10.1016\/j.neunet.2025.107794_b58","series-title":"Exploring extreme parameter compression for pre-trained language models","author":"Ren","year":"2022"},{"key":"10.1016\/j.neunet.2025.107794_b59","doi-asserted-by":"crossref","unstructured":"Rennie, S. J., Marcheret, E., Mroueh, Y., Ross, J., & Goel, V. (2017). Self-critical sequence training for image captioning. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7008\u20137024).","DOI":"10.1109\/CVPR.2017.131"},{"key":"10.1016\/j.neunet.2025.107794_b60","series-title":"Resource-efficient neural networks for embedded systems","author":"Roth","year":"2020"},{"key":"10.1016\/j.neunet.2025.107794_b61","series-title":"Parameter sharing methods for multilingual self-attentional translation models","author":"Sachan","year":"2018"},{"key":"10.1016\/j.neunet.2025.107794_b62","series-title":"Poor man\u2019s bert: Smaller and faster transformer models","author":"Sajjad","year":"2020"},{"key":"10.1016\/j.neunet.2025.107794_b63","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4510\u20134520).","DOI":"10.1109\/CVPR.2018.00474"},{"key":"10.1016\/j.neunet.2025.107794_b64","series-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"10.1016\/j.neunet.2025.107794_b65","series-title":"Exploring challenges of deploying BERT-based NLP models in resource-constrained embedded devices","author":"Sarkar","year":"2023"},{"key":"10.1016\/j.neunet.2025.107794_b66","series-title":"Proceedings of the 54th annual meeting of the association for computational linguistics (volume 1: long papers)","first-page":"1715","article-title":"Neural machine translation of rare words with subword units","author":"Sennrich","year":"2016"},{"key":"10.1016\/j.neunet.2025.107794_b67","first-page":"8815","article-title":"Q-bert: Hessian based ultra low precision quantization of bert","volume":"vol. 34","author":"Shen","year":"2020"},{"key":"10.1016\/j.neunet.2025.107794_b68","series-title":"Patient knowledge distillation for bert model compression","author":"Sun","year":"2019"},{"key":"10.1016\/j.neunet.2025.107794_b69","series-title":"Mobilebert: a compact task-agnostic bert for resource-limited devices","author":"Sun","year":"2020"},{"key":"10.1016\/j.neunet.2025.107794_b70","doi-asserted-by":"crossref","unstructured":"Suzuki, J., & Nagata, M. (2016). Learning Compact Neural Word Embeddings by Parameter Space Sharing.. In IJCAI (pp. 2046\u20132052).","DOI":"10.18653\/v1\/N16-1135"},{"key":"10.1016\/j.neunet.2025.107794_b71","series-title":"2021 24th Euromicro conference on digital system design","first-page":"449","article-title":"Improving the efficiency of transformers for resource-constrained devices","author":"Tabani","year":"2021"},{"key":"10.1016\/j.neunet.2025.107794_b72","doi-asserted-by":"crossref","unstructured":"Tahaei, M., Charlaix, E., Nia, V., Ghodsi, A., & Rezagholizadeh, M. (2022). KroneckerBERT: Significant compression of pre-trained language models through kronecker decomposition and knowledge distillation. In Proceedings of the 2022 conference of the North American chapter of the association for computational linguistics: human language technologies (pp. 2116\u20132127).","DOI":"10.18653\/v1\/2022.naacl-main.154"},{"key":"10.1016\/j.neunet.2025.107794_b73","series-title":"Proceedings of the 57th annual meeting of the association for computational linguistics","first-page":"4593","article-title":"BERT rediscovers the classical NLP pipeline","author":"Tenney","year":"2019"},{"key":"10.1016\/j.neunet.2025.107794_b74","series-title":"What do you learn from context? probing for sentence structure in contextualized word representations","author":"Tenney","year":"2019"},{"key":"10.1016\/j.neunet.2025.107794_b75","series-title":"Advances in neural information processing systems","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neunet.2025.107794_b76","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., & Parikh, D. (2015). Cider: Consensus-based image description evaluation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4566\u20134575).","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"10.1016\/j.neunet.2025.107794_b77","series-title":"SDBERT: SparseDistilBERT, a faster and smaller BERT model","author":"Vinoda","year":"2022"},{"key":"10.1016\/j.neunet.2025.107794_b78","series-title":"Minilmv2: Multi-head self-attention relation distillation for compressing pretrained transformers","author":"Wang","year":"2020"},{"key":"10.1016\/j.neunet.2025.107794_b79","series-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","author":"Wang","year":"2018"},{"key":"10.1016\/j.neunet.2025.107794_b80","series-title":"2021 International joint conference on neural networks","first-page":"1","article-title":"Refbert: Compressing bert by referencing to pre-computed representations","author":"Wang","year":"2021"},{"key":"10.1016\/j.neunet.2025.107794_b81","first-page":"170","article-title":"Ontonotes release 5.0 ldc2013t19","volume":"23","author":"Weischedel","year":"2013","journal-title":"Linguistic Data Consortium, Philadelphia, PA"},{"key":"10.1016\/j.neunet.2025.107794_b82","series-title":"International conference on machine learning","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","author":"Xiao","year":"2023"},{"key":"10.1016\/j.neunet.2025.107794_b83","series-title":"Bert-of-theseus: Compressing bert by progressive module replacing","author":"Xu","year":"2020"},{"key":"10.1016\/j.neunet.2025.107794_b84","series-title":"2019 Fifth workshop on energy efficient machine learning and cognitive computing-neurIPS edition","first-page":"36","article-title":"Q8bert: Quantized 8bit bert","author":"Zafrir","year":"2019"},{"key":"10.1016\/j.neunet.2025.107794_b85","series-title":"Ternarybert: Distillation-aware ultra-low bit bert","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2025.107794_b86","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128140","article-title":"You only compress once: Towards effective and elastic BERT compression via exploit\u2013explore stochastic nature gradient","volume":"599","author":"Zhang","year":"2024","journal-title":"Neurocomputing"},{"issue":"14","key":"10.1016\/j.neunet.2025.107794_b87","doi-asserted-by":"crossref","first-page":"6171","DOI":"10.3390\/app14146171","article-title":"MicroBERT: Distilling moe-based knowledge from BERT into a lighter model","volume":"14","author":"Zheng","year":"2024","journal-title":"Applied Sciences"},{"key":"10.1016\/j.neunet.2025.107794_b88","series-title":"BERT learns to teach: Knowledge distillation with meta learning","author":"Zhou","year":"2021"},{"key":"10.1016\/j.neunet.2025.107794_b89","series-title":"Moebert: from bert to mixture-of-experts via importance-guided adaptation","author":"Zuo","year":"2022"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025006744?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025006744?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T04:04:26Z","timestamp":1762315466000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025006744"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":89,"alternative-id":["S0893608025006744"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107794","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Embeddings hidden layers learning for neural network compression","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107794","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"107794"}}