{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T12:48:16Z","timestamp":1763729296928,"version":"3.45.0"},"publisher-location":"Singapore","reference-count":54,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543663","type":"print"},{"value":"9789819543670","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-4367-0_19","type":"book-chapter","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T12:37:21Z","timestamp":1763728641000},"page":"276-289","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Revisiting 16-Bit Neural Network Training: A Practical Approach for\u00a0Resource-Limited Learning"],"prefix":"10.1007","author":[{"given":"Juyoung","family":"Yun","sequence":"first","affiliation":[]},{"given":"Sol","family":"Choi","sequence":"additional","affiliation":[]},{"given":"Francois","family":"Rameau","sequence":"additional","affiliation":[]},{"given":"Byungkon","family":"Kang","sequence":"additional","affiliation":[]},{"given":"Zhoulai","family":"Fu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"key":"19_CR1","unstructured":"Association, I.S.: IEEE P3109: Standard for arithmetic formats for machine learning (2024). https:\/\/standards.ieee.org\/ieee\/3109\/11010\/. Accessed: May 30 2024"},{"key":"19_CR2","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems. vol.\u00a033, pp. 1877\u20131901 (2020). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Hu, X., Zhou, H., Xu, N.: FxpNet: training a deep convolutional neural network in fixed-point representation. In: Proceedings of the International Joint Conference on Neural Networks (2017)","DOI":"10.1109\/IJCNN.2017.7966159"},{"key":"19_CR4","unstructured":"Choi, J., Wang, Z., Venkataramani, S., Chuang, P., Srinivasa, V., Gopalakrishnan, K.: Pact: parameterized clipping activation for quantized neural networks. In: International Conference on Learning Representations (2018)"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"19_CR6","unstructured":"Courbariaux, M., Bengio, Y., David, J.P.: BinaryConnect: training deep neural networks with binary weights during propagations. In: Proceedings of Neural Information Processing Systems (2015)"},{"key":"19_CR7","unstructured":"t Courbariaux, M., Bengio, Y., David, J.P.: Binaryconnect: training deep neural networks with binary weights during propagations. In: Advances in Neural Information Processing Systems, pp. 3123\u20133131 (2015)"},{"key":"19_CR8","unstructured":"Das, D., et al: Mixed precision training of convolutional neural networks using integer operations. In: Proceedings of International Conference on Learning Representations (2018)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"De\u00a0Sa, C., Feldman, M., R , C., Olukotun, K.: Understanding and optimizing asynchronous low-precision stochastic gradient descent. In: Proceedings of International Symposium on Computer Architecture (2017)","DOI":"10.1145\/3079856.3080248"},{"key":"19_CR10","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., Zettlemoyer, L.: LLM.int8(): 8-bit matrix multiplication for transformers at scale. In: Advances in Neural Information Processing Systems (2024)"},{"key":"19_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"19_CR12","unstructured":"FriendliAI: Meta-llama-3-70b-fp8. Hugging Face (2024). https:\/\/huggingface.co\/FriendliAI\/Meta-Llama-3-70B-fp8. Accessed 30 May 2024"},{"key":"19_CR13","unstructured":"Gale, T., Elsen, E., Hooker, S.: The state of sparsity in deep neural networks. In: International Conference on Learning Representations (2019)"},{"key":"19_CR14","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016)"},{"key":"19_CR15","unstructured":"Google: Mixed precision training guide (2023), available at: https:\/\/www.tensorflow.org\/guide\/mixed_precision. Accessed 15 Aug 2023"},{"key":"19_CR16","unstructured":"Gupta, S., Agrawal, A., Gopalakrishnan, K., Narayanan, P.: Deep learning with limited numerical precision. In: Proceedings of International Conference on Machine Learning (2015)"},{"key":"19_CR17","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems, pp. 1135\u20131143 (2015)"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Proceedings of the European Conference on Computer Vision (2016)","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"19_CR19","doi-asserted-by":"publisher","unstructured":"Higham, N.J.: Accuracy and Stability of Numerical Algorithms. Society for Industrial and Applied Mathematics, second edn. (2002). https:\/\/doi.org\/10.1137\/1.9780898718027, https:\/\/epubs.siam.org\/doi\/abs\/10.1137\/1.9780898718027","DOI":"10.1137\/1.9780898718027"},{"key":"19_CR20","unstructured":"Hinton, G.: Neural networks for machine learning (2018) https:\/\/www.cs.toronto.edu\/~tijmen\/csc321\/slides\/lecture_slides_lec6.pdf, lecture 6a: Overview of mini-batch gradient descent"},{"key":"19_CR21","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop (2015). http:\/\/arxiv.org\/abs\/1503.02531"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2018.00286"},{"key":"19_CR24","unstructured":"Kingma, D.P., Ba., J.L.: Adam: A method for stochastic optimization. In: Proceedings of International Conference on Learning Representations (2015)"},{"key":"19_CR25","unstructured":"Koster, U., et\u00a0al.: Bf16: Revisiting bf16 training. In: Proceedings of the International Conference on Machine Learning (2020)"},{"key":"19_CR26","volume-title":"Learning Multiple Layers of Features from Tiny Images","author":"A Krizhevsky","year":"2009","unstructured":"Krizhevsky, A., Hinton, G.: Learning Multiple Layers of Features from Tiny Images. University of Toronto, Tech. rep. (2009)"},{"key":"19_CR27","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 25, 1097\u20131105 (2012)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR28","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of Neural Information Processing Systems (2012)"},{"key":"19_CR29","unstructured":"K ster, U., et al.: Flexpoint: an adaptive numerical format for efficient training of deep neural networks. In: Proceedings of Neural Information Processing Systems (2017)"},{"key":"19_CR30","doi-asserted-by":"publisher","unstructured":"Liao, B., Monz, C.: ApiQ: Finetuning of 2-bit quantized large language model. Arxiv Preprint (2024). https:\/\/doi.org\/10.48550\/ARXIV.2402.05147","DOI":"10.48550\/ARXIV.2402.05147"},{"key":"19_CR31","unstructured":"Lin, D.D., Talathi, S.S., Annapureddy, V.S.: Fixed point quantization of deep convolutional networks. In: Proceedings of the International Conference on Machine Learning (2016)"},{"key":"19_CR32","doi-asserted-by":"publisher","unstructured":"Ma, S., et al.: The era of 1-bit LLMs: All large language models are in 1.58 bits. Arxiv Preprint (2024). https:\/\/doi.org\/10.48550\/ARXIV.2402.17764","DOI":"10.48550\/ARXIV.2402.17764"},{"key":"19_CR33","unstructured":"Micikevicius, P., et al.: Mixed precision training. In: Proceedings of International Conference on Learning Representations (2018)"},{"key":"19_CR34","unstructured":"NVIDIA: NVIDIA ampere ga102 gpu architecture (2020), available at: https:\/\/www.nvidia.com\/content\/PDF\/nvidia-ampere-ga-102-gpu-architecture-whitepaper-v2.pdf. Accessed 27 Sep 2024"},{"key":"19_CR35","unstructured":"NVIDIA: Train with mixed precision (2023), available at: https:\/\/docs.nvidia.com\/deeplearning\/performance\/mixed-precision-training\/index.html. Accessed 15 Aug 2023"},{"key":"19_CR36","unstructured":"NVIDIA: Tensor cores (2024), available at: https:\/\/www.nvidia.com\/en-gb\/data-center\/tensor-cores\/. Accessed 27 Sept 2024"},{"key":"19_CR37","unstructured":"NVIDIA: Tuning cuda applications for nvidia ampere gpu architecture (2024), available at: https:\/\/docs.nvidia.com\/cuda\/ampere-tuning-guide\/index.html. Accessed 27 Sept 2024"},{"key":"19_CR38","doi-asserted-by":"publisher","unstructured":"Padgett, W.T., Anderson, D.V.: Fixed-Point Signal Processing. Synthesis Lectures on Signal Processing, Springer Cham, 1 edn. (2009). https:\/\/doi.org\/10.1007\/978-3-031-02533-4","DOI":"10.1007\/978-3-031-02533-4"},{"key":"19_CR39","unstructured":"PyTorch: Accelerating llama3 fp8 inference with triton kernels. PyTorch Blog (2024). https:\/\/pytorch.org\/blog\/accelerating-llama3\/. Accessed 30 May 30 2024"},{"issue":"4","key":"19_CR40","first-page":"861","volume":"6","author":"N Qian","year":"1999","unstructured":"Qian, N.: A method for speeding up the convergence of back-propagation learning. Neural Netw. 6(4), 861\u2013867 (1999)","journal-title":"Neural Netw."},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: Imagenet classification using binary convolutional neural networks. In: European Conference on Computer Visio, pp. 525\u2013542 (2016)","DOI":"10.1007\/978-3-319-46493-0_32"},{"issue":"1","key":"19_CR42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11265-018-1423-2","volume":"91","author":"S Ristov","year":"2019","unstructured":"Ristov, S., Malkin, E., Zilic, Z.: Efficient deep learning inference on embedded systems using fixed-point arithmetic on fpgas. J. Signal Process. Syst. 91(1), 1\u201313 (2019)","journal-title":"J. Signal Process. Syst."},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Sharma, H., et al.: Bit Fusion: Bit-level dynamically composable architecture for accelerating deep neural networks. In: Proceedings of International Symposium on Computer Architecture (2017)","DOI":"10.1109\/ISCA.2018.00069"},{"key":"19_CR45","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of International Conference on Learning Representations (2015)"},{"key":"19_CR46","unstructured":"Computer Society, I.: IEEE standard for floating-point arithmetic. IEEE Std 754-2019 (Revision of IEEE 754-2008), pp. 1\u201384 (2019)"},{"key":"19_CR47","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., J\u00e9gou, H.: Training data-efficient image transformers and distillation through attention. In: International Conference on Machine Learning (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"19_CR48","unstructured":"Wang, N., Choi, J., Brand, D., Chen, C.Y., Gopalakrishnan, K.: Training deep neural networks with 8-bit floating point numbers. In: Proceedings of the International Conference on Neural Information Processing Systems, pp. 7686\u20137695 (2018)"},{"key":"19_CR49","unstructured":"Wu, S., Li, G., Chen, F., Shi, L.: Training and inference with integers in deep neural networks. In: Proceedings of International Conference on Learning Representations (2018)"},{"key":"19_CR50","unstructured":"Xi, H., Li, C., Chen, J., Zhu, J.: Training transformers with 4-bit integers. In: Advances in Neural Information Processing Systems (2024)"},{"key":"19_CR51","unstructured":"Xiao, G., Lin, J., Seznec, M., Wu, H., Demouth, J., Han, S.: SmoothQuant: accurate and efficient post-training quantization for large language models. In: Proceedings of the International Conference on Machine Learning (2023)"},{"key":"19_CR52","doi-asserted-by":"crossref","unstructured":"Zafrir, D., Boudoukh, G., Izsak, P., Wasserblat, M.: Q8BERT: Quantized 8bit BERT. In: Proceedings of the 5th Workshop on Energy Efficient Machine Learning and Cognitive Computing-NeurIPS 2019, pp. 36\u201339 (2019)","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"19_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, W., Liu, C., Ma, Y., Zhang, F., Li, S., Zhang, Y.: Ternarybert: distillation-aware ultra-low bit bert. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, pp. 509\u2013521 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.37"},{"key":"19_CR54","unstructured":"Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., Zou, Y.: DoReFa-Net: training low bitwidth convolutional neural networks with low bitwidth gradients. In: Arxiv Preprint (2016)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4367-0_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T12:37:41Z","timestamp":1763728661000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4367-0_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,22]]},"ISBN":["9789819543663","9789819543670"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4367-0_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,22]]},"assertion":[{"value":"22 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}