Meta-learning, or learning to learn, is the science of systematically observing how different machine learning approaches perform on a wide range of learning tasks, and then learning from this experience, or meta-data, to learn new tasks much faster than otherwise possible. Not only does this dramatically speed up and improve the design of machine learning pipelines or neural architectures, it also allows us to replace hand-engineered algorithms with novel approaches learned in a data-driven way. In this chapter, we provide an overview of the state of the art in this fascinating and continuously evolving field.

There is a larger number of vehicles in the streets The number of traffic jams is rising Tons of greenhouse gases are emitted to the atmosphere The citizens' quality of life is decreasing Daniel H. Stolfi Bio-inspired Computing and Smart Mobility October 2018 1 / 73 5. Scientific and Technological Bases 6. Scientific and Technological Bases Smart Mobility Problems Smart Mobility Problems – The Challenge Long travel times Polluted cities Fuel economy Finding an available car park spot We are focused on Smart Mobility and Smart Environment Daniel H. Stolfi Bio-inspired Computing and Smart Mobility October 2018 2 / 73 7. Scientific and Technological Bases Metaheuristics Metaheuristics Daniel H. Stolfi Bio-inspired Computing and Smart Mobility October 2018 3 / 73 8. Scientific and Technological Bases Microsimulation Traffic Simulators Can be categorized as: Macroscopic Mesoscopic Microscopic After a deep study we selected SUMO (Simulation of Urban MObility) http://dlr.de/ts/sumo/ Daniel H. Stolfi Bio-inspired Computing and Smart Mobility October 2018 4 / 73 9. Scientific and Technological Bases SUMO: Simulation of Urban MObility SUMO Open Source (German Aerospace Center - DLR) Several car following models Maps can be imported from OpenStreetMap Lots of data can be retrieved after the simulation Externally controlled by TraCI Daniel H. Stolfi Bio-inspired Computing and Smart Mobility October 2018 5 / 73 10. Scientific and Technological Bases SUMO: Simulation of Urban MObility Building Mobility Scenarios with SUMO 1 Download the map from OpenStreetMap 2 Clean the irrelevant elements using JOSM 3 Import the city model using NETCONVERT 4 Define its routes using DUAROUTER We call it the experts' solution (computed by SUMO's DUAROUTER) Daniel H. Stolfi Bio-inspired Computing and Smart Mobility October 2018 6 / 73 11. Scientific and Technological Bases Incomplete Maps and Data Incomplete Maps and Data PROBLEM: How reliable are the simulation scenarios? OUR PROPOSAL: Maps imported from OpenStreetMap Vehicular flows calculated according to data published by local councils Flow Generator Algorithm (FGA)* * Original contribution of this PhD thesis Daniel H. Stolfi Bio-inspired Computing and Smart Mobility October 2018 7 / 73 12. Scientific and Technological Bases Incomplete Maps and Data Flow Generator Algorithm (FGA) Contributions: Flow Generator Algorithm Route Generator Set of mobility scenarios Daniel H. Stolfi Bio-inspired Computing and Smart Mobility October 2018 8 / 73 13.

Memetic Computing is a subject in computer science which considers complex structures as the combination of simple agents, memes, whose evolutionary interactions lead to intelligent structures capable of problem-solving. This paper focuses on Memetic Computing optimization algorithms and proposes a counter-tendency approach for algorithmic design. Research in the field tends to go in the direction of improving existing algorithms by combining different methods or through the formulation of more complicated structures. Contrary to this trend, we instead focus on simplicity, proposing a structurally simple algorithm with emphasis on processing only one solution at a time. The proposed algorithm, namely Three Stage Optimal Memetic Exploration, is composed of three memes; the first stochastic and with a long search radius, the second stochastic and with a moderate search radius and the third deterministic and with a short search radius. This is suggestive of the fact that complexity in algorithmic structures can be unnecessary, if not detrimental, and that simple bottom-up approaches are likely to be competitive is here invoked as an extension to Memetic Computing basing on the philosophical concept of Ockham's Razor. An extensive experimental setup on various test problems and one digital signal processing application is presented. Numerical results show that the proposed approach, despite its simplicity and low computational cost displays a very good performance on several problems, and is competitive with sophisticated algorithms representing the-state-of-the-art in computational intelligence optimization. Key words: Memetic Computing, Evolutionary Algorithms, Memetic Algorithms, Computational intelligence Optimization 1. Introduction Emerging technologies in computer science and engineering, as well as the demands of the market and the society, often impose the solution, in the every day life, of complex optimization problems. The complexity of today's problems is due to various reasons such as high non-linearities, high multi-modality, large scale, noisy fitness landscape, computationally expensive fitness functions, real-time demands, and limited hardware available(e.g. when the computational device is portable and cheap). In these cases, the use of exact methods is unsuitable because, in general, there is not sufficient prior knowledge (hypotheses) on the optimization problem; thus, computational intelligence approaches become not only advisable but often the only alternative to face the optimization. Scientific research in computational intelligence optimization can be classified into two general categories.

Deep neuroevolution and deep reinforcement learning (deep RL) algorithms are two popular approaches to policy search. The former is widely applicable and rather stable, but suffers from low sample efficiency. By contrast, the latter is more sample efficient, but the most sample efficient variants are also rather unstable and highly sensitive to hyper-parameter setting. So far, these families of methods have mostly been compared as competing tools. However, an emerging approach consists in combining them so as to get the best of both worlds. Two previously existing combinations use either a standard evolutionary algorithm or a goal exploration process together with the DDPG algorithm, a sample efficient off-policy deep RL algorithm. In this paper, we propose a different combination scheme using the simple cross-entropy method (CEM) and TD3, another off-policy deep RL algorithm which improves over DDPG. We evaluate the resulting algorithm, CEM-RL, on a set of benchmarks classically used in deep RL. We show that CEM-RL benefits from several advantages over its competitors and offers a satisfactory trade-off between performance and sample efficiency.

Software defined networking (SDN) represents a promising networking architecture that combines central management and network programmability. SDN separates the control plane from the data plane and moves the network management to a central point, called the controller, that can be programmed and used as the brain of the network. Recently, the research community has showed an increased tendency to benefit from the recent advancements in the artificial intelligence (AI) field to provide learning abilities and better decision making in SDN. In this study, we provide a detailed overview of the recent efforts to include AI in SDN. Our study showed that the research efforts focused on three main sub-fields of AI namely: machine learning, meta-heuristics and fuzzy inference systems. Accordingly, in this work we investigate their different application areas and potential use, as well as the improvements achieved by including AI-based techniques in the SDN paradigm.

This paper introduces DATA Agent, a system which creates murder mystery adventures from open data. In the game, the player takes on the role of a detective tasked with finding the culprit of a murder. All characters, places, and items in DATA Agent games are generated using open data as source content. The paper discusses the general game design and user interface of DATA Agent, and provides details on the generative algorithms which transform linked data into different game objects. Findings from a user study with 30 participants playing through two games of DATA Agent show that the game is easy and fun to play, and that the mysteries it generates are straightforward to solve.

Traditional A/B testing can be biased in terms of results and limited in terms of designs available for testing. Ultimately, someone has to choose something, and if you end up choosing two ineffective sites for testing, the results will be meaningless. But not so for RateCity, which engaged an artificial intelligence (AI) solution via Sentient for a recent site testing, which resulted in a 51 per cent uplift in conversions. The solution was so successful, the home loan conversino website is applying the solution across its various verticals moving in the future. Like many businesses, RateCity could see the value in A/B testing, but didn't have the time or resources with its small team to undertake the amount of testing required in-house.

Abstract--Hanabi is a cooperative card game with hidden information that has won important awards in the industry and received some recent academic attention. A two-track competition of agents for the game will take place in the 2018 CIG conference. In this paper, we develop a genetic algorithm that builds rulebased agents by determining the best sequence of rules from a fixed rule set to use as strategy. In three separate experiments, we remove human assumptions regarding the ordering of rules, add new, more expressive rules to the rule set and independently evolve agents specialized at specific game sizes. As result, we achieve scores superior to previously published research for the mirror and mixed evaluation of agents. Game-playing agents have a long tradition of serving as benchmarks for AI research. However, traditionally most of the focus has been on competitive, perfect information games, such as Checkers [1], Chess [2] and Go [3]. Cooperative games with imperfect information provide an interesting research topic not only due to the added challenges posed to researchers, but also because many modern industrial and commercial applications can be characterized as examples of cooperation between humans and machines in order to achieve a mutual goal in an uncertain environment. In this paper, we address a particularly interesting cooperative game with partial information: Hanabi [4].

A "Hive Mind" of Doctors, moderated by AI algorithms, makes more accurate diagnoses than the Doctors or Machine Learning alone, according to a new study from Stanford and Unanimous AI For more info visit www.unanimous.ai

In the real world, the environment is constantly changing with the input variables under the effect of noise. However, few algorithms were shown to be able to work under those circumstances. Here, Novelty-Organizing Team of Classifiers (NOTC) is applied to the continuous action mountain car as well as two variations of it: a noisy mountain car and an unstable weather mountain car. These problems take respectively noise and change of problem dynamics into account. Moreover, NOTC is compared with NeuroEvolution of Augmenting Topologies (NEAT) in these problems, revealing a trade-off between the approaches. While NOTC achieves the best performance in all of the problems, NEAT needs less trials to converge. It is demonstrated that NOTC achieves better performance because of its division of the input space (creating easier problems). Unfortunately, this division of input space also requires a bit of time to bootstrap.