artificial intelligence

SIBYL >
AI>
Methods >
Story >
Game >
Club>
Space>
Authors >

SIBYL

SIBYL is Artificial Intelligence that proposes new stories and generates new compositions. SIBYL is trained by techniques of composing by Pynchon, Burroughs, Gibson and Xenakis. The project offers an innovative fusion between four domains: storytelling, games design, experimental music and artificial intelligence. The project creates and tests new methods of generating music, stories and new types of audio-visual performance through interactions with autonomous AI agent. SIBYL is presented as performance and interactive installation that uses recurrent neural networks, reinforcement learning and analog sound-video synthesizers.

AI

We observe the success of artificial neural networks in simulating human performance on a number of tasks: such as image recognition, natural language processing, etc. However, today's AI algorithms are limited in how much previous knowledge they are able to keep through each new training
phase and how much they can reuse. In practice this means that it is necessary to build and adjust new algorithms to every new particular task. Processes such as intuition, emotions, planning, thinking and abstraction are a part of processes, which occur in the human brain. A generalization in AI means that system can generate new compositions or find solutions for new tasks that are not present in the training corpus. "General" means that one AI program realizes number of different tasks and the same code can be use in many applications. We must focus on self-improvement techniques e.g. reinforcement learning and integrate it with deep learning, recurrent neural networks, reinforced random walks.

Methods

The project will use formal methods from computer science to create a model and AI program for the generation of new stories and game scenarios. Different AI techniques will be tested during residency. The Model is created with the use of Recurrent Neural Networks and Deep Reinforcement Learning. DL simulates the process of generalization. I incorporated the Reinforcement Learning process into Deep Learning for creating a system that will have an ability to learn and self improve.

Story

The main objective of this project is to research and develop new forms of storytelling and game scenarios by developing a new dimension of artificial intelligence (AI) and machine learning which will lead to the development of new techniques in the area of storytelling, games design, media arts and performance. The project proposes precise solutions for the understanding of story, automatic creation of stories and the creation of interactional narrative experiences. This proposal investigates the storytelling potential of human beings interacting with an AI agent in a natural language as a possible foundation for establishing the best way for humans and machines to interact overall. Communication with an AI agent, accompanied by an understanding of human activities, is an important area within the future of storytelling, games, creative communication and media arts. I will create intelligent game in which the participants create unknown paths and associations.

Game

The game consists in going through a labyrinth of ideas, ideograms and symbols, which have to be deciphered in ordered the player to move to a new place. The player encounters queries, riddles, jokes, icons, pictures; "obstacles".

Club

The project is focused on the process of collaboration itself and on participation in the environment, in which different sources and materials are transformed in real time by a group of artists-hackers-players. The system is open because of the stream of data and the stream of artists: local artists, hackers and musicians are invited to transform the space into open club.

SPACE

An integral part of the project is the multidimensional presentation of project in architecture.

Authors

development: Robert B. Lisek
coding: Robert B. Lisek
support: IO Lab Stavanger, ARE Enschede, Adam Mickiewicz Institute
contact: lisek at fundamental dot art dot pl

produced by Robert B. Lisek & Fundamental Research Lab