Manuel Cebrian

JAIR Journal 2021 Journal Article

Superintelligence Cannot be Contained: Lessons from Computability Theory

• Manuel Alfonseca
• Manuel Cebrian
• Antonio Fernandez Anta
• Lorenzo Coviello
• Andrés Abeliuk
• Iyad Rahwan

Superintelligence is a hypothetical agent that possesses intelligence far surpassing that of the brightest and most gifted human minds. In light of recent advances in machine intelligence, a number of scientists, philosophers and technologists have revived the discussion about the potentially catastrophic risks entailed by such an entity. In this article, we trace the origins and development of the neo-fear of superintelligence, and some of the major proposals for its containment. We argue that total containment is, in principle, impossible, due to fundamental limits inherent to computing itself. Assuming that a superintelligence will contain a program that includes all the programs that can be executed by a universal Turing machine on input potentially as complex as the state of the world, strict containment requires simulations of such a program, something theoretically (and practically) impossible. This article is part of the special track on AI and Society.

IJCAI Conference 2018 Conference Paper

TuringBox: An Experimental Platform for the Evaluation of AI Systems

• Ziv Epstein
• Blakeley H. Payne
• Judy Hanwen Shen
• Casey Jisoo Hong
• Bjarke Felbo
• Abhimanyu Dubey
• Matthew Groh
• Nick Obradovich

We introduce TuringBox, a platform to democratize the study of AI. On one side of the platform, AI contributors upload existing and novel algorithms to be studied scientifically by others. On the other side, AI examiners develop and post machine intelligence tasks to evaluate and characterize the outputs of algorithms. We outline the architecture of such a platform, and describe two interactive case studies of algorithmic auditing on the platform.

AAAI Conference 2010 Conference Paper

The Genetic Algorithm as a General Diffusion Model for Social Networks

• Mayank Lahiri
• Manuel Cebrian

Diffusion processes taking place in social networks are used to model a number of phenomena, such as the spread of human or computer viruses, and the adoption of products in ‘viral marketing’ campaigns. It is generally difficult to obtain accurate information about how such spreads actually occur, so a variety of stochastic diffusion models are used to simulate spreading processes in networks instead. We show that a canonical genetic algorithm with a spatially distributed population, when paired with specific forms of Holland’s synthetic hyperplane-defined objective functions, can simulate a large and rich class of diffusion models for social networks. These include standard diffusion models, such as the independent cascade and competing processes models. In addition, our genetic algorithm diffusion model (GADM) can also model complex phenomena such as information diffusion. We demonstrate an application of the GADM to modeling information flow in a large, dynamic social network derived from e-mail headers.

AAAI Conference 2008 Conference Paper

Protein Structure Prediction on the Face Centered Cubic Lattice by Local Search

• Manuel Cebrian
• Pascal Van Hentenryck

Ab initio protein structure prediction is an important problem for which several algorithms have been developed. Algorithms differ by how they represent 3D protein conformations (on-lattice, off-lattice, coarse-grain or fine-grain model), by the energy model they consider, and whether they are heuristic or exact algorithms. This paper presents a local search algorithm to find the native state for the Hydrophobic-Polar (HP) model on the Face Centered Cubic (FCC) lattice; i. e. a self-avoiding walk on the FCC lattice with maximum number of H-H contacts. The algorithm relies on a randomized, structured initialization, a novel fitness function to guide the search, and efficient data structures to obtain self-avoiding walks. Experimental results on benchmark instances show the efficiency and excellent performance of our algorithm, and illustrate the biological pertinence of the FCC lattice.

IJCAI Conference 2003 Conference Paper

Channeling Constraints and Value Ordering in the Quasi Group Completion Problem

• Ivan Dotu
• Alvaro del Val
• Manuel Cebrian