Artificial Intelligence Applications in Engineering (MUH-920), week 13 of 14: interactive lab
Prof. Dr. Utku Kose, Süleyman Demirel University
Part A learns byte-pair merges from engineering sentences and shows how any typed text splits into tokens [1]. Part B turns next-token scores into probabilities with an adjustable temperature and top-k cut, and samples continuations. Part C retrieves passages from a small engineering knowledge base with TF-IDF and assembles an answer that cites them, as retrieval-augmented generation does [2, 3].
Context: "The concrete cubes were tested after twenty eight ..."
Six questions with instant feedback. Rate your confidence before checking each answer.
Answers are saved in this browser only. The export creates a Markdown learning log for your portfolio.
After the export, continue with the discipline challenge and the weekly task in the week overview.
[1] Sennrich, R., Haddow, B., & Birch, A. (2016). Neural machine translation of rare words with subword units. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (pp. 1715-1725). https://doi.org/10.18653/v1/P16-1162
[2] Manning, C. D., Raghavan, P., & Schütze, H. (2008). Introduction to Information Retrieval. Cambridge University Press.
[3] Lewis, P., Perez, E., Piktus, A., et al. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Processing Systems 33 (pp. 9459-9474). https://arxiv.org/abs/2005.11401
[4] Ouyang, L., Wu, J., Jiang, X., et al. (2022). Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems 35 (pp. 27730-27744). https://arxiv.org/abs/2203.02155
[5] Ji, Z., Lee, N., Frieske, R., et al. (2023). Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12), 248. https://doi.org/10.1145/3571730