Professor Thomas Müller and Professor Hans Briegel have been carrying out research on a machine learning model for several years that differs significantly from alternative artificial intelligence (AI) learning models. The philosopher from Konstanz and the theoretical physicist from the University of Innsbruck have integrated methods of philosophical action theory and quantum optics. Their "Projective Simulation" learning model has already been successfully applied in basic research. Together with the Innsbruck physicist Dr. Katja Ried, the researchers have now adapted this AI model for realistic application to biological systems. The current issue of the scientific journal PLoS One discusses how the learning model can be used to model and reproduce locusts' specific swarming behaviour.

This course is about the fundamental concepts of artificial intelligence. This topic is getting very hot nowadays because these learning algorithms can be used in several fields from software engineering to investment banking. Learning algorithms can recognize patterns which can help detecting cancer for example. We may construct algorithms that can have a very good guess about stock price movement in the market. In the first chapter we are going to talk about the basic graph algorithms.

This paper revisits the Bayesian CMA-ES and provides updates for normal Wishart. It emphasizes the difference between a normal and normal inverse Wishart prior. After some computation, we prove that the only difference relies surprisingly in the expected covariance. We prove that the expected covariance should be lower in the normal Wishart prior model because of the convexity of the inverse. We present a mixture model that generalizes both normal Wishart and normal inverse Wishart model. We finally present various numerical experiments to compare both methods as well as the generalized method.

Computational swarm intelligence consists of multiple artificial simple agents exchanging information while exploring a search space. Despite a rich literature in the field, with works improving old approaches and proposing new ones, the mechanism by which complex behavior emerges in these systems is still not well understood. This literature gap hinders the researchers' ability to deal with known problems in swarms intelligence such as premature convergence, and the balance of coordination and diversity among agents. Recent advances in the literature, however, have proposed to study these systems via the network that emerges from the social interactions within the swarm (i.e., the interaction network). In our work, we propose a definition of the interaction network for the Artificial Bee Colony (ABC) algorithm. With our approach, we captured striking idiosyncrasies of the algorithm. We uncovered the different patterns of social interactions that emerge from each type of bee, revealing the importance of the bees variations throughout the iterations of the algorithm. We found that ABC exhibits a dynamic information flow through the use of different bees but lacks continuous coordination between the agents.

A key stepping stone in the development of an artificial general intelligence (a machine that can perform any task), is the production of agents that can perform multiple tasks at once instead of just one. Unfortunately, canonical methods are very prone to catastrophic forgetting (CF) - the act of overwriting previous knowledge about a task when learning a new task. Recent efforts have developed techniques for overcoming CF in learning systems, but no attempt has been made to apply these new techniques to evolutionary systems. This research presents a novel technique, weight protection, for reducing CF in evolutionary systems by adapting a method from learning systems. It is used in conjunction with other evolutionary approaches for overcoming CF and is shown to be effective at alleviating CF when applied to a suite of reinforcement learning tasks. It is speculated that this work could indicate the potential for a wider application of existing learning-based approaches to evolutionary systems and that evolutionary techniques may be competitive with or better than learning systems when it comes to reducing CF.

This paper presents Automatic Algorithm Discoverer (AAD), an evolutionary framework for synthesizing programs of high complexity. To guide evolution, prior evolutionary algorithms have depended on fitness (objective) functions, which are challenging to design. To make evolutionary progress, instead, AAD employs Problem Guided Evolution (PGE), which requires introduction of a group of problems together. With PGE, solutions discovered for simpler problems are used to solve more complex problems in the same group. PGE also enables several new evolutionary strategies, and naturally yields to High-Performance Computing (HPC) techniques. We find that PGE and related evolutionary strategies enable AAD to discover algorithms of similar or higher complexity relative to the state-of-the-art. Specifically, AAD produces Python code for 29 array/vector problems ranging from min, max, reverse, to more challenging problems like sorting and matrix-vector multiplication. Additionally, we find that AAD shows adaptability to constrained environments/inputs and demonstrates outside-of-the-box problem solving abilities.

Game-based benchmarks have been playing an essential role in the development of Artificial Intelligence (AI) techniques. Providing diverse challenges is crucial to push research toward innovation and understanding in modern techniques. Rinascimento provides a parameterised partially-observable multiplayer card-based board game, these parameters can easily modify the rules, objectives and items in the game. We describe the framework in all its features and the game-playing challenge providing baseline game-playing AIs and analysis of their skills. We reserve to agents' hyper-parameter tuning a central role in the experiments highlighting how it can heavily influence the performance. The base-line agents contain several additional contribution to Statistical Forward Planning algorithms.

Sentiment analysis consists of evaluating opinions or statements from the analysis of text. Among the methods used to estimate the degree in which a text expresses a given sentiment, are those based on Gaussian Processes. However, traditional Gaussian Processes methods use a predefined kernel with hyperparameters that can be tuned but whose structure can not be adapted. In this paper, we propose the application of Genetic Programming for evolving Gaussian Process kernels that are more precise for sentiment analysis. We use use a very flexible representation of kernels combined with a multi-objective approach that simultaneously considers two quality metrics and the computational time spent by the kernels. Our results show that the algorithm can outperform Gaussian Processes with traditional kernels for some of the sentiment analysis tasks considered.

I am honestly not sure whether fish have any concept of bees. I am equally unsure whether bees have any concept of fish. I am even more unsure whether bees and fish could be friends, if they knew that the other existed. But thanks to robots, it turns out that the answer is definitely yes. The video really doesn't communicate a whole lot about what's going on here, but the central question is whether robots can usefully mediate communications between groups of very different animals in such a way that long distance interspecies collective behavior becomes possible. The answer appears to be yes, which isn't a total surprise: We've known for a while that robots can communicate with both bees and zebra fish, in the sense that the actions of a robot that mimics the behavior of an animal can, in turn, predictably and interactively alter the animals' behavior.

With the development of computational intelligence [1, 2, 19, 26], nature-inspired algorithms have been shown to be effective and thus become widely used for various optimization problems [15, 17, 2]. However, there is still a significant gap between theory and practice. Though the applications of algorithms are very successful, the relevant fundamental theory lacks behind or no theory at all. For example, the bat algorithm (BA), developed by Xin-She Yang in 2010 [3, 4], has been shown to very efficient in practice, but there is no mathematical theory for analyzing this algorithm. In fact, most of the swarm intelligence based algorithms for computational intelligence have no or little theoretical analyses, except for a few algorithms, such as the well known particle swarm optimization [10, 12, 25, 27] and genetic algorithms [16, 34]. Though we know these algorithms can work well in practice, we rarely understand why they work so well and under what conditions or parameter ranges. These key challenges require further in-depth theoretical studies.