Abstract
Lately, with the public release of Chat GPT-2,3,4 many people agree that not enough attention given to the power and importance of the machinery that Mathematics brings, especially Discrete and Pure Mathematics. From simple ability to capture the essence, capacity to compress the information to its expertise in grasping the representational structure of entities, objects to projection of text blobs into the unified vector space. Mathematics mechanism to generalize can cover as a foundation in making significant progress in the area of AGI (artificial general intelligence), applications of embedding can lead quickly to very short roll out to production environment the varies of recommendation systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sutskever, I., Vinyals, O., Le, Q.V.: Generating sequences with recurrent neural networks. In: Proceedings of the International Conference on Learning Representations (ICLR), pp. 1–14 (2013). https://doi.org/10.1162/ICLR.2013.14
Karpukhin, V., et al.: Dense Passage Retrieval for Open-Domain Question Answering. CoRR, abs/2004.04906 (2020). https://arxiv.org/abs/2004.04906
Chang, W.-C., Yu, F.X., Chang, Y.-W., Yang, Y., Kumar, S.: Pre-training tasks for embedding-based large-scale retrieval. In: Proceedings of the International Conference on Learning Representations (ICLR) (2020). Published as a conference paper at ICLR 2020. https://openreview.net/forum?id=BJeDY0NFwS
Cer, D., et al.: Universal Sentence Encoder. arXiv preprint arXiv:1803.11175 (2018). https://doi.org/10.48550/arXiv.1803.11175
Conneau, A., Kiela, D., Schwenk, H., Barrault, L., Bordes, A.: Supervised Learning of Universal Sentence Representations from Natural Language Inference Data. arXiv preprint arXiv:1705.02364 (2017). https://doi.org/10.48550/arXiv.1705.02364. arXiv: https://arxiv.org/abs/1705.02364
Mac Lane, S.: Categories for the Working Mathematician. https://en.wikipedia.org/wiki/Category_theory.10
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kalinichenko, V. (2024). Leverage Mathematics’ Capability to Compress and Generalize as Application of ML Embedding Extraction from LLMs and Its Adaptation in the Automotive Space. In: Nicosia, G., Ojha, V., La Malfa, E., La Malfa, G., Pardalos, P.M., Umeton, R. (eds) Machine Learning, Optimization, and Data Science. LOD 2023. Lecture Notes in Computer Science, vol 14505. Springer, Cham. https://doi.org/10.1007/978-3-031-53969-5_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-53969-5_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53968-8
Online ISBN: 978-3-031-53969-5
eBook Packages: Computer ScienceComputer Science (R0)