Arte Generativa

Imagem d@ Cristiano Pires Patrício [Ficheiro Local]
Cristiano Pires Patrício
Código:
16794
Ano:
3
Semestre:
S1
Créditos ECTS:
6
Carga Horária:
PL(30H)/T(30H)
Área Científica:
INFORMÁTICA E DESIGN
Learning outcomes:
The main general objective of this course unit (UC) is the following:

1) Develop in students a holistic view of generative computer systems in creative practices in visual arts, performing arts, design, digital games, etc.

With regard to the specific objectives, and after completing this UC, students should be able to:

1) meet artists and their works in visual arts, performing arts, internet-art and generative art;
2) understand the artistic potential of technological tools;
3) understand, articulate and discuss social, ethical and philosophical issues involving computational creativity and generative artistic practices;
4) identify, describe, evaluate, criticize and contrast generative artworks and computationally creative systems;
5) use artificial intelligence to generate artistic material;
6) implement and test generative art systems;
7) develop an interactive art piece.
Syllabus:
1) Art and creativity: history, artists and their techniques, the creative processes in art, artistic languages, generative art history.
2) Introduction to AI and Generative Arts.
3) Introduction to Deep Learning and Neural Networks.
4) Generative Arts: Conventional and Deep Learning Approaches: Conventional generative arts: theories and applications; Deep Learning for Generative Arts: from CNN to AutoEncoder, VAE, and GAN; Image synthesis: Image-to-Image Translation, Pix2Pix, CycleGAN; Case studies: Deep Dream.
5) Neural Artistic Style Modelling: Content vs. style, feature extraction, texture synthesis, pastiche; Neural style transfer with BigGAN and StyleGAN.
6) Generative Arts across Modalities: Text content generation: Bert and GPT models; Music generation: basics and case studies; Motion and dance Generation: basics and case studies.
7) Evaluation methods for computational creativity.
8) Societal and philosophical perspectives.
Teaching Methodologies and Assessment Criteria:
Teaching Methodologies:
- Lectures (TE);
- Practical laboratory classes (PL);
- Project-based learning;
- Independent study;
- Tutorial support (clarification of questions) for students.

As this is a course unit with both theoretical and practical components, lectures will be used to present the scheduled topics, supported by audiovisual resources. Practical exercises using software for the generation of creative materials will also be provided. Students will receive guidance and support throughout the development of their projects.
Main Bibliography:
1) K. Brennan (2011), Creative computing: A design-based introduction to computational thinking. Available at http://tinyurl.com/brennancc.
2) B. Groß, H. Bohnacker, J. Laub, and C. Lazzeroni (2018), Generative design: visualize, program, and create with JavaScript in p5. js, Chronicle Books.
3) P. Machado, J. Romero, and G. Greenfield (2021), Artificial Intelligence and the Arts. Springer International Publishing.
4) J. Maeda (2005), Creative code, Thames and Hudson.
5) J. Parker and S. Diamond (2020), Generative art: algorithms as artistic tool, Durvile & UpRoute Books.
6) J. Parker (2023), Generative Art for Python, Uproute.
7) M. Pearson (2011), Generative art: a practical guide using Processing, Simon and Schuster Publishers.
8) Foster, D. (2023). Generative deep learning: Teaching machines to paint, write, compose, and play (2nd ed.). O'Reilly Media.
Language:
Portuguese. Tutorial support is available in English.
Esta informação promove os seguintes Objetivos de Desenvolvimento Sustentável da ONU:
Garantir o acesso à educação inclusiva, de qualidade e equitativa, e promover oportunidades de aprendizagem ao longo da vida para todos