求學階段的過往經歷讓我對藝術與科技領域充滿興趣，並嘗試探索兩者之間的合作關係。藉由自我剖析，重新了解自己的成長環境和所遇到的相關人、事、物，重新理解與認識延伸、再發展。並從研究學習中，發現藝術創作的新視界，於是乎「人工智慧」成為我在藝術創作主要媒材。
人工智慧應用於藝術的發展在國外有許多嘗試，從這些作品中可以看見藝術家創作的理念與脈絡。這些創作影響了我的思考方向，並嘗試以傳統水墨畫結合人工智慧技術進行藝術創作。對於生成圖像的成果與藝術家梅洛龐蒂所提到的「空間」以及水墨畫表現的「空間感」不謀而合，也因此確立了創作的媒材——水墨與機器學習。
以自身的學習歷程作為創作理念，並在作品的創作發展過程中，透過資料之操作，觀察模型的變化以及訓練生成影像與看見。透過系列作品呈現人工智慧模型在訓練過程中產出的影像並以此探究模型不同階段的變化，試圖了解人工智慧訓練時學習的方式。
創作過程中發展為三個系列系列一自然成長、系列二影像剪影、系列三畫中空間。最後以這些系列創作為基礎發展成最終的展覽成果《INK-SIGHT, MY SIGHT》。此作品是以傳統水墨結合機器學習發展的一系列創作，將東方傳統繪畫以新的方式呈現，加入新科技發展「成長」之創作主題。以此探究人工智慧之相關課題，藉由展覽傳遞創作者所要表達之議題，同時引發大眾重新省思新科技。
從這些人工智慧模型所生成的水墨影像紀錄，看見模型的變化與成長，從不同的生成影像中看見彼此學習之差異，並藉由《INK-SIGHT, MY SIGHT》展覽探究人工智慧與生成藝術之相關議題。以參與國際研討會的經驗，深入探索人工智慧藝術之創作，並反思自己的創作以及未來的創作發展方向。

Artists have always been early adopters of new technologies. I wish to inject AI technologies into ink wash painting and explore the ancient art with new mediums. Through case studies and literature review, the Generative Adversarial Network (GAN) was identified as the basic machine learning framework. In particular, the pix2pixHD implementation was adopted to train my painting machine. The dataset required for training should be organized in painting-photo pairs. The art project began from installing and testing the operations of pix2pixHD machine learning programs; creating ink wash paintings and preparing training datasets; to training and testing painting machines. 500 ink wash paintings were painted to incrementally train painting machines. While working with the first painting machine, it is noticed the machine learned outcomes with appearance of shadow or silhouette, or with spatial quality. This led to further dataset preparations and the training of painting machines. It is through these interactive processes of training and testing painting machines, I was able to reflect on my own ink wash painting styles from observing images generated by painting machines. These painting machines served as an inspirational tool during my art creation processes. I explored the three series of painting machines, examined qualities of digital ink wash paintings generated, and discussed the relationship between me, the artist, and the machines I grew.

AIArtists.org. (2021a). Our Featured Artists. AIArtists.Org. https://aiartists.org/ai-artist-founding-members
AIArtists.org. (2021b). Refik Anadol. AIArtists.Org. https://aiartists.org/refik-anadol
AIArtists.org. (2021c). Tom White. AIArtists.Org. https://aiartists.org/tom-white
AIArtists.org. (2021d). Anna Ridler. AIArtists.Org. https://aiartists.org/anna-ridler
Anadol, R. (2023). WDCH Dreams. REFIK ANDOL. https://refikanadol.com/works/wdch-dreams/
Brain, T. (2018). The environment is not a system. A Peer-Reviewed Journal About, 7(1), 152–165. https://doi.org/10.7146/aprja.v7i1.116062
Cetinic, E., & She, J. (2022). Understanding and creating art with AI: review and outlook. ACM Transactions on Multimedia Computing, Communications, and Applications, 18(2), 1–22. https://doi.org/10.1145/3475799
Crespo, S. (2020). Neural zoo. In Selected Works (pp. 6–8). https://drive.google.com/file/d/1ljhMkE2Fy0lZd_Bk5Z_D017QIKfAByb1/view
Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., & Bharath, A. A. (2018).
Generative adversarial networks: an overview. IEEE Signal Processing Magazine, 35(1), 53–65. https://doi.org/10.1109/MSP.2017.2765202
Crowson, K., Ingham, M., Letts, A., & Spirin, A. (2022). Disco Diffusion (v5.4.0). https://github.com/alembics/disco-diffusion
Deep Dream Generator. (2023). Deep Dream Generator. Website. https://deepdreamgenerator.com/
Dhariwal, P., & Nichol, A. (2021). Diffusion models beat GANs on image synthesis. In M. Ranzato, A. Beygelzimer, Y. Dauphin, P. S. Liang, & J. W. Vaughan (Eds.), Advances in Neural Information Processing Systems (Vol. 34, pp. 8780–8794). Curran Associates, Inc. https://proceedings.neurips.cc/paper/2021/file/49ad23d1ec9fa4bd8d77d02681df5cfa-Paper.pdf
Draper, S. W. (1978). The Penrose triangle and a family of related figures. Perception, 7(3), 283–296. https://doi.org/10.1068/p070283
Hertzmann, A. (2020). Visual indeterminacy in GAN art. ACM SIGGRAPH 2020 Art Gallery, 53(4), 424–428. https://doi.org/10.1145/3386567.3388574
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 5967–5976. https://doi.org/10.1109/CVPR.2017.632
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
Lehar, S. M. (2003). The World in Your Head: A Gestalt View of the Mechanism of Conscious Experience. Lawrence Erlbaum Associates.
Li, L. (2022). The impact of artificial intelligence painting on contemporary art from Disco Diffusion’s painting creation experiment. 2022 International Conference on Frontiers of Artificial Intelligence and Machine Learning (FAIML), 52–56. https://doi.org/10.1109/FAIML57028.2022.00020
Midjourney. (n.d.). Midjourney. Website. Retrieved July 31, 2022, from https://www.midjourney.com/home/
Oppenlaender, J. (2022). The creativity of text-to-image generation. 25th International Academic
Mindtrek Conference, 192–202. https://doi.org/10.1145/3569219.3569352
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In M. Meila & T. Zhang (Eds.), Proceedings of the 38th International Conference on Machine Learning (Vol. 139, pp. 8748–8763). PMLR. https://proceedings.mlr.press/v139/radford21a.html
Ridler, A. (2018). Myriad (Tulips). Anna Ridler. http://annaridler.com/myriad-tulips
Ridler, A. (2019). Mosaic Virus. Anna Ridler. http://annaridler.com/mosaic-virus
Snell, B. (2018). Dio. Ben Snell. http://bensnell.io/dio
Tyka, M. (2019). Us and Them. Mike Tyka. https://miketyka.com/?p=usandthem
Wang, T.-C., Liu, M.-Y., Zhu, J.-Y., Tao, A., Kautz, J., & Catanzaro, B. (2018). High-resolution image synthesis and semantic manipulation with conditional GANs. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8798–8807. https://doi.org/10.1109/CVPR.2018.00917
White, T. (2018). Perception Engines. Dribnet. https://drib.net/perception-engines
White, T. (2021). Perception Engines II. Dribnet. https://drib.net/perception-engines-2021
WikiArt. (n.d.a). Waterfall by Escher. In WikiArt: Visual Art Encyclopedia. Retrieved January 25, 2023, from https://www.wikiart.org/en/m-c-escher/waterfall
WikiArt. (n.d.b). Ascending & Descending by Escher. In WikiArt: Visual Art Encyclopedia. Retrieved January 25, 2023, from https://www.wikiart.org/en/m-c-escher/ascending-descending
安海姆（1982）。藝術與視覺心理學（李長俊 譯）。雄獅圖書公司。（原著出版於1974年）
李開復、王詠剛（2017）。人工智慧來了。遠見天下文化。
梅洛-庞蒂（2001）。知觉现象学（姜志辉 譯）。商务印书馆。（原著出版於1945年）
郭超、鲁越、林懿伦、卓凡、王飞跃（2019）。平行艺术：人机协作的艺术创作。智能科学与技术学报，1（4），335–341。https://doi.org/10.11959/j.issn.2096-6652.201938
單維彰（2020）。文化脈絡中的數學。國立中央大學出版中心。
黃柏翰（2002）。梅洛龐蒂《知覺現象學》的空間觀之研究（碩士論文，國立中央大學）。國立中央大學圖書館。http://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=88124011
楊朝明（2001）。空間美感的表現手法在平面設計中運用之研究（碩士論文，國立臺灣師範大學）。臺灣碩博士論文知識加值系統。https://hdl.handle.net/11296/vz2z4u
劉梅琴（2011）。中國藝術思維的現代闡釋─從「意象」到「格式塔」（GestaIt）。臺北大學中文學報，10，67–94。https://doi.org/10.29766/JCLLNTU.201109.0005
蔡芯圩、陳怡安（2015）。用年表讀通西洋藝術史。商周出版。
謝赫（1983）。古畫品錄（國立故宮博物院藏本影印）。台灣商務。
簡聖芬、張天豪（2020）。人工智慧科技介入的藝術創作歷程：科技為工具與科技為媒材的探討。政府研究資訊系統。https://www.grb.gov.tw/search/planDetail？id=13517936