2.1. Exploration: Collection of Bibliographic Materials

The collection of bibliographic materials was conducted through the systematic exploration of academic databases:

  1. Google Scholar;
  2. Semantic Scholar;
  3. Researchgate;
  4. ArXiv.org.

To get search results, the keyword strings were used:

Citation network mapping was employed as a secondary research method. References cited within identified papers were examined for additional relevant sources. Some of them often pointed to breaking through papers (Lecun et al. 1998; Goodfellow et al. 2014; Vaswani et al. 2017; Karras, Laine, and Aila 2019), systematic surveys (Lin et al. 2021; Achraf Oussidi and Azeddine Elhassouny 2018; Sarker 2021) and books (Goodfellow, Ian, Bengio, Yoshua, and Courville, Aaron 2016; Pascal Wichmann 2021).

The selection process prioritised materials based on their relevance to font generation, technical depth, and connection to typography principles. Each source was evaluated against these criteria to ensure the highest standard of academic rigour and practical applicability.

Contemporary artificial intelligence tools were integrated into the research process. The OpenAI API playground (“OpenAI Platform,” n.d.) was employed for research synthesis, whilst Perplexity (“Perplexity,” n.d.) aided in literature searches. These tools served as supplementary resources, helping to process and synthesise information, though their outputs required careful verification against primary sources.

Documentation of findings was facilitated through Zotero (“Zotero,” n.d.) for reference management, complemented by the Zettelkasten method for note-taking (“The Zettelkasten Manual,” n.d.) alongside with Obsidian (“Obsidian - Sharpen Your Thinking,” n.d.) and its plugins (Montes 2021; Khoo [2022] 2022). This systematic approach to documentation allowed for flexible organisation and cross-referencing of materials, ensuring comprehensive coverage of the subject matter.

This methodological approach to knowledge collection has established a foundation for understanding the intersection of artificial intelligence and type design, whilst acknowledging the limitations inherent in bibliographic research methods.

Achraf Oussidi, and Azeddine Elhassouny. 2018. “Deep Generative Models: Survey.” In 2018 International Conference on Intelligent Systems and Computer Vision (ISCV), 1–8. https://doi.org/10.1109/ISACV.2018.8354080.
Goodfellow, Ian J., Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. “Generative Adversarial Networks.” June 10, 2014. https://doi.org/10.48550/arXiv.1406.2661.
Goodfellow, Ian, Bengio, Yoshua, and Courville, Aaron. 2016. Deep Learning. MIT Press. https://www.deeplearningbook.org/.
Karras, Tero, Samuli Laine, and Timo Aila. 2019. “A Style-Based Generator Architecture for Generative Adversarial Networks.” March 29, 2019. https://doi.org/10.48550/arXiv.1812.04948.
Khoo, Richie. (2022) 2022. “Obsidian Pandoc Academic Workflow Guide.” https://github.com/evolve2k/obsidian-pandoc-academic-word-doc-guide/blob/59882a65ed298f37e1d89cf7d9f2f6a44bbeac8b/setup-zotero-obsidian.md.
Lecun, Y., L. Bottou, Y. Bengio, and P. Haffner. 1998. “Gradient-Based Learning Applied to Document Recognition.” Proceedings of the IEEE 86 (11): 2278–2324. https://doi.org/10.1109/5.726791.
Lin, Tianyang, Yuxin Wang, Xiangyang Liu, and Xipeng Qiu. 2021. “A Survey of Transformers.” June 15, 2021. https://doi.org/10.48550/arXiv.2106.04554.
Montes, Mariana. 2021. “Obsidian and Zotero.” Mariana Montes. October 23, 2021. https://www.marianamontes.me/post/obsidian-and-zotero/.
“Obsidian - Sharpen Your Thinking.” n.d. Accessed January 3, 2025. https://obsidian.md/.
“OpenAI Platform.” n.d. Accessed June 22, 2023. https://platform.openai.com.
Pascal Wichmann. 2021. “Deep Learning with Vector Graphics.” Book. Deep Learning with Vector Graphics. 2021. https://pwichmann.github.io/deep-learning-with-vector-graphics-book.
“Perplexity.” n.d. Perplexity AI, Inc. Accessed December 24, 2022. https://www.perplexity.ai/.
Sarker, Iqbal H. 2021. “Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions.” SN Computer Science 2 (6): 420. https://doi.org/10.1007/s42979-021-00815-1.
“The Zettelkasten Manual.” n.d. The Zettelkasten Manual. Accessed January 3, 2025. https://thezettelkasten.com/.
Vaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. “Attention Is All You Need.” In Advances in Neural Information Processing Systems. Vol. 30. Curran Associates, Inc. https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html.
“Zotero.” n.d. Corporation for Digital Scholarship. Accessed January 3, 2025. https://www.zotero.org/.

License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License .

Creative Commons License

Citation

If this work is useful for your research, please cite it as:

@phdthesis{paldia2025generative,
  title={Research and development of generative neural networks for type design},
  author={Paldia, Filip},
  year={2025},
  school={Academy of Fine Arts and Design in Bratislava},
  address={Bratislava, Slovakia},
  type={Doctoral thesis},
  url={https://lttrface.com/doctoral-thesis/},
  note={Department of Visual Communication, Studio Typo}
}