Deep Learning 101 - AI4VisualArts

Summary:
Artificial intelligence (AI) for visual arts marks a transformative phase in technology and creative fields for some time. Initially, generative systems from the domain of Evolutionary Computing pioneered the collaboration between computational methods and art. These systems, which predated the use of machine learning (ML), laid the foundational work for advanced computational techniques in visual arts. As the field evolved, early machine learning applications emerged, typically enhancing evaluation systems of generative art systems. Several projects during this phase demonstrated the potential of ML to assist in the generation process. Deep learning approaches and early generative machine learning models such as GANs and style transfer networks kickstarted the generative AI we see today. Impactful works utilizing deep learning technologies began redefining visual arts' boundaries and possibilities. These projects leveraged artificial neural network architectures to create image outputs that could learn from vast datasets and generate visually compelling pieces that reflect complex patterns not immediately discernible by human artists. Currently, the frontier of AI in visual arts is marked by the emergence of latent diffusion models, such as Stable Diffusion, and multimodal models like ChatGPT (via Dall-E) and Gemini. These systems incorporate multi-model architectures that enable interactions between textual and visual data, offering groundbreaking possibilities for users to create different visual outputs of arguable aesthetic merit. Looking forward, the convergence of AI technologies promises to enhance artistic creativity and image creation, enabling individuals to engage with visual arts in innovative ways. The continuous evolution of generative models is expected to further blur the lines between creator and creation, setting the stage for future explorations that could redefine art in the digital age.

Speaker:
João Correia is an Assistant Professor at the University of Coimbra, a researcher of the Computational Design and Visualization Lab, and a member of the Evolutionary and Complex Systems (ECOS) of the Centre for Informatics and Systems of the same university (CISUC). Moreover, he is also currently Deputy Director of CISUC. He holds a PhD in Information Science and Technology from the University of Coimbra since 2018. His main research interests include Evolutionary Computation, Machine Learning, Generative Models, Evolutionary Machine Learning, Adversarial Learning, and Computational Creativity. He is involved in different international program committees of international conferences in the area of Evolutionary Computation, Artificial Intelligence and Computational Art and Creativity and reviewer for different conferences and journals for the mentioned areas, namely GECCO, EvoStar and ICCC. He was also publicity chair and chair of the International Conference of Evolutionary Art Music and Design conference, chair of the International Conference on the Applications of Evolutionary Computation and publicity chair for EvoStar - The Leading European Event on Bio-Inspired Computation. He is also an executive member of SPECIES society - the Society for the Promotion of Evolutionary Computation in Europe and its Surroundings. Furthermore, he has authored and co-authored several articles on the different International Conferences and journals on Artificial Intelligence and Evolutionary Computation and is involved in national and international projects concerning Evolutionary Computation, Machine Learning and Data Science.

Meetup info:
We expect up to 45 minutes of talk, with around 15 minutes in the end for the Q&A. The talk recording will be streamed on our Youtube page. The presentation content will be available on our GitHub page.
We hope that you'll join us!