On the Democratization of AI: Bridging the Gap with AutoML

Riding the wave of recent groundbreaking achievements, artificial intelligence (AI) is currently the buzzword on everybody’s lips and, allowing algorithms to learn from historical data, Machine Learning (ML) emerged as its pinnacle. The multitude of algorithms, each with unique strengths and weaknesses, highlights the absence of a universal solution and poses a challenging optimization problem. In response, automated machine learning (AutoML) navigates vast search spaces within minimal time constraints. By lowering entry barriers, AutoML emerged as promising the democratization of AI, yet facing some challenges. In data-centric AI, the discipline of systematically engineering data used to build an AI system, the challenge of configuring data pipelines is rather simple. We devise a methodology for building effective data pre-processing pipelines in supervised learning as well as a data-centric AutoML solution for unsupervised learning. In human-centric AI, many current AutoML tools were not built around the user but rather around algorithmic ideas, raising ethical and social bias concerns. We contribute by deploying AutoML tools aiming at complementing, instead of replacing, human intelligence. In particular, we provide solutions for single-objective and multi-objective optimization and showcase the challenges and potential of novel interfaces featuring large language models. Finally, there are application areas that rely on numerical simulators, often related to earth observations, they tend to be particularly high-impact and address important challenges such as climate change and crop life cycles. We commit to coupling these physical simulators with (Auto)ML solutions towards a physics-aware AI. Specifically, in precision farming, we design a smart irrigation platform that: allows real-time monitoring of soil moisture, predicts future moisture values, and estimates water demand to schedule the irrigation.

Passive Solar Building Design Using Genetic Programming

Passive solar building design is the process of designing a building while considering sunlight exposure for receiving heat in winter and rejecting heat in summer. The main goal of a passive solar building design is to remove or reduce the need of mechanical and electrical systems for cooling and heating, and therefore saving energy costs and reducing environmental impact. This research will use evolutionary computation to design passive solar buildings. Evolutionary design is used in many research projects to build 3D models for structures automatically. In this research, we use a mixture of split grammar and string-rewriting for generating new 3D structures. To evaluate energy costs, the EnergyPlus system is used. This is a comprehensive building energy simulation system, which will be used alongside the genetic programming system. In addition, genetic programming will also consider other design and geometry characteristics of the building as search objectives, for example, window placement, building shape, size, and complexity. In passive solar designs, reducing energy that is needed for cooling and heating are two objectives of interest. Experiments show that smaller buildings with no windows and skylights are the most energy efficient models. Window heat gain is another objective used to encourage models to have windows. In addition, window and volume based objectives are tried. To examine the impact of environment on designs, experiments are run on five different geographic locations. Also, both single floor models and multi-floor models are examined in this research. According to the experiments, solutions from the experiments were consistent with respect to materials, sizes, and appearance, and satisfied problem constraints in all instances.

A hybridised evolutionary algorithm for multi-criterion minimum spanning tree problems

A hybridised and Knowledge-based Evolutionary Algorithm (KEA) is applied to the multi-criterion minimum spanning tree problems. Hybridisation is used across its three phases. In the first phase a deterministic single objective optimization algorithm finds the extreme points of the Pareto front. In the second phase a K-best approach finds the first neighbours of the extreme points, which serve as an elitist parent population to an evolutionary algorithm in the third phase. A knowledge-based mutation operator is applied in each generation to reproduce individuals that are at least as good as the unique parent. The advantages of KEA over previous algorithms include its speed (making it applicable to large real-world problems), its scalability to more than two criteria, and its ability to find both the supported and unsupported optimal solutions.

Gains from switching and evolutionary stability in multi-player matrix games.

In this paper we unify, simplify, and extend previous work on the evolutionary dynamics of symmetric N-player matrix games with two pure strategies. In such games, gains from switching strategies depend, in general, on how many other individuals in the group play a given strategy. As a consequence, the gain function determining the gradient of selection can be a polynomial of degree N-1. In order to deal with the intricacy of the resulting evolutionary dynamics, we make use of the theory of polynomials in Bernstein form. This theory implies a tight link between the sign pattern of the gains from switching on the one hand and the number and stability of the rest points of the replicator dynamics on the other hand. While this relationship is a general one, it is most informative if gains from switching have at most two sign changes, as is the case for most multi-player matrix games considered in the literature. We demonstrate that previous results for public goods games are easily recovered and extended using this observation. Further examples illustrate how focusing on the sign pattern of the gains from switching obviates the need for a more involved analysis.

An Analysis of black-box optimization problems in reinsurance: evolutionary-based approaches

Black-box optimization problems (BBOP) are de ned as those optimization problems in which the objective function does not have an algebraic expression, but it is the output of a system (usually a computer program). This paper is focussed on BBOPs that arise in the eld of insurance, and more speci cally in reinsurance problems. In this area, the complexity of the models and assumptions considered to de ne the reinsurance rules and conditions produces hard black-box optimization problems, that must be solved in order to obtain the optimal output of the reinsurance. The application of traditional optimization approaches is not possible in BBOP, so new computational paradigms must be applied to solve these problems. In this paper we show the performance of two evolutionary-based techniques (Evolutionary Programming and Particle Swarm Optimization). We provide an analysis in three BBOP in reinsurance, where the evolutionary-based approaches exhibit an excellent behaviour, nding the optimal solution within a fraction of the computational cost used by inspection or enumeration methods.

A new compact linear programming formulation for choice network revenue management

The choice network revenue management model incorporates customer purchase behavioras a function of the offered products, and is the appropriate model for airline and hotel networkrevenue management, dynamic sales of bundles, and dynamic assortment optimization.The optimization problem is a stochastic dynamic program and is intractable. A certainty-equivalencerelaxation of the dynamic program, called the choice deterministic linear program(CDLP) is usually used to generate dyamic controls. Recently, a compact linear programmingformulation of this linear program was given for the multi-segment multinomial-logit (MNL)model of customer choice with non-overlapping consideration sets. Our objective is to obtaina tighter bound than this formulation while retaining the appealing properties of a compactlinear programming representation. To this end, it is natural to consider the affine relaxationof the dynamic program. We first show that the affine relaxation is NP-complete even for asingle-segment MNL model. Nevertheless, by analyzing the affine relaxation we derive a newcompact linear program that approximates the dynamic programming value function betterthan CDLP, provably between the CDLP value and the affine relaxation, and often comingclose to the latter in our numerical experiments. When the segment consideration sets overlap,we show that some strong equalities called product cuts developed for the CDLP remain validfor our new formulation. Finally we perform extensive numerical comparisons on the variousbounds to evaluate their performance.

The evolutionary host switches of Polychromophilus: a multi-gene phylogeny of the bat malaria genus suggests a second invasion of mammals by a haemosporidian parasite.

BACKGROUND: The majority of Haemosporida species infect birds or reptiles, but many important genera, including Plasmodium, infect mammals. Dipteran vectors shared by avian, reptilian and mammalian Haemosporida, suggest multiple invasions of Mammalia during haemosporidian evolution; yet, phylogenetic analyses have detected only a single invasion event. Until now, several important mammal-infecting genera have been absent in these analyses. This study focuses on the evolutionary origin of Polychromophilus, a unique malaria genus that only infects bats (Microchiroptera) and is transmitted by bat flies (Nycteribiidae). METHODS: Two species of Polychromophilus were obtained from wild bats caught in Switzerland. These were molecularly characterized using four genes (asl, clpc, coI, cytb) from the three different genomes (nucleus, apicoplast, mitochondrion). These data were then combined with data of 60 taxa of Haemosporida available in GenBank. Bayesian inference, maximum likelihood and a range of rooting methods were used to test specific hypotheses concerning the phylogenetic relationships between Polychromophilus and the other haemosporidian genera. RESULTS: The Polychromophilus melanipherus and Polychromophilus murinus samples show genetically distinct patterns and group according to species. The Bayesian tree topology suggests that the monophyletic clade of Polychromophilus falls within the avian/saurian clade of Plasmodium and directed hypothesis testing confirms the Plasmodium origin. CONCLUSION: Polychromophilus' ancestor was most likely a bird- or reptile-infecting Plasmodium before it switched to bats. The invasion of mammals as hosts has, therefore, not been a unique event in the evolutionary history of Haemosporida, despite the suspected costs of adapting to a new host. This was, moreover, accompanied by a switch in dipteran host.

Using spatially distributed parameters and multi-response objective functions to solve parameterization of complex applications of semi-distributed hydrological models

Application of semi-distributed hydrological models to large, heterogeneous watersheds deals with several problems. On one hand, the spatial and temporal variability in catchment features should be adequately represented in the model parameterization, while maintaining the model complexity in an acceptable level to take advantage of state-of-the-art calibration techniques. On the other hand, model complexity enhances uncertainty in adjusted model parameter values, therefore increasing uncertainty in the water routing across the watershed. This is critical for water quality applications, where not only streamflow, but also a reliable estimation of the surface versus subsurface contributions to the runoff is needed. In this study, we show how a regularized inversion procedure combined with a multiobjective function calibration strategy successfully solves the parameterization of a complex application of a water quality-oriented hydrological model. The final value of several optimized parameters showed significant and consistentdifferences across geological and landscape features. Although the number of optimized parameters was significantly increased by the spatial and temporal discretization of adjustable parameters, the uncertainty in water routing results remained at reasonable values. In addition, a stepwise numerical analysis showed that the effects on calibration performance due to inclusion of different data types in the objective function could be inextricably linked. Thus caution should be taken when adding or removing data from an aggregated objective function.

Multi-axis solutions in packaging machines in Europe

The objective of this thesis was to examine the potential of multi-axis solutions in packaging machines produced in Europe. The definition of a multi-axis solution in this study is a construction that uses a common DC bus power supply for different amplifiers running the axes and the intelligence is centralized into one unit. The cost structure of a packaging machine was gained from an automation research, which divided the machines according to automation categories. The automation categories were then further divided into different sub-components by evaluating the ratio of multi-axis solutions compared to other automation components in packaging machines. A global motion control study was used for further information. With the help of the ratio, an estimation of the potential of multi-axis solutions in each country and packaging machine sector was completed. In addition to the research, a specific questionnaire was sent to five companies to gain information about the present situation and possible trends in packaging machinery. The greatest potential markets are in Germany and Italy, which are also the largest producers of packaging machinery in Europe. The greatest growth in the next few years will be seen in Turkey where the annual growth rate equals the general machinery production rate in Asia. The greatest market potential of the Nordic countries is found in Sweden in 35th position on the list. According to the interviews, motion control products in packaging machines will retain their current power levels, as well as the number of axes in the future. Integrated machine safety features together with a universal programming language are the desired attributes of the future. Unlike generally in industry, the energy saving objectives are and will remain insignificant in the packaging industry.

Approches générales de résolution pour les problèmes multi-attributs de tournées de véhicules et confection d'horaires

Thèse réalisée en cotutelle entre l'Université de Montréal et l'Université de Technologie de Troyes

Domain/Multi-Domain Protection and Provisioning in Optical Networks

L’évolution récente des commutateurs de sélection de longueurs d’onde (WSS -Wavelength Selective Switch) favorise le développement du multiplexeur optique d’insertionextraction reconfigurable (ROADM - Reconfigurable Optical Add/Drop Multiplexers) à plusieurs degrés sans orientation ni coloration, considéré comme un équipement fort prometteur pour les réseaux maillés du futur relativement au multiplexage en longueur d’onde (WDM -Wavelength Division Multiplexing ). Cependant, leur propriété de commutation asymétrique complique la question de l’acheminement et de l’attribution des longueur d’ondes (RWA - Routing andWavelength Assignment). Or la plupart des algorithmes de RWA existants ne tiennent pas compte de cette propriété d’asymétrie. L’interruption des services causée par des défauts d’équipements sur les chemins optiques (résultat provenant de la résolution du problème RWA) a pour conséquence la perte d’une grande quantité de données. Les recherches deviennent ainsi incontournables afin d’assurer la survie fonctionnelle des réseaux optiques, à savoir, le maintien des services, en particulier en cas de pannes d’équipement. La plupart des publications antérieures portaient particulièrement sur l’utilisation d’un système de protection permettant de garantir le reroutage du trafic en cas d’un défaut d’un lien. Cependant, la conception de la protection contre le défaut d’un lien ne s’avère pas toujours suffisante en termes de survie des réseaux WDM à partir de nombreux cas des autres types de pannes devenant courant de nos jours, tels que les bris d’équipements, les pannes de deux ou trois liens, etc. En outre, il y a des défis considérables pour protéger les grands réseaux optiques multidomaines composés de réseaux associés à un domaine simple, interconnectés par des liens interdomaines, où les détails topologiques internes d’un domaine ne sont généralement pas partagés à l’extérieur. La présente thèse a pour objectif de proposer des modèles d’optimisation de grande taille et des solutions aux problèmes mentionnés ci-dessus. Ces modèles-ci permettent de générer des solutions optimales ou quasi-optimales avec des écarts d’optimalité mathématiquement prouvée. Pour ce faire, nous avons recours à la technique de génération de colonnes afin de résoudre les problèmes inhérents à la programmation linéaire de grande envergure. Concernant la question de l’approvisionnement dans les réseaux optiques, nous proposons un nouveau modèle de programmation linéaire en nombres entiers (ILP - Integer Linear Programming) au problème RWA afin de maximiser le nombre de requêtes acceptées (GoS - Grade of Service). Le modèle résultant constitue celui de l’optimisation d’un ILP de grande taille, ce qui permet d’obtenir la solution exacte des instances RWA assez grandes, en supposant que tous les noeuds soient asymétriques et accompagnés d’une matrice de connectivité de commutation donnée. Ensuite, nous modifions le modèle et proposons une solution au problème RWA afin de trouver la meilleure matrice de commutation pour un nombre donné de ports et de connexions de commutation, tout en satisfaisant/maximisant la qualité d’écoulement du trafic GoS. Relativement à la protection des réseaux d’un domaine simple, nous proposons des solutions favorisant la protection contre les pannes multiples. En effet, nous développons la protection d’un réseau d’un domaine simple contre des pannes multiples, en utilisant les p-cycles de protection avec un chemin indépendant des pannes (FIPP - Failure Independent Path Protecting) et de la protection avec un chemin dépendant des pannes (FDPP - Failure Dependent Path-Protecting). Nous proposons ensuite une nouvelle formulation en termes de modèles de flots pour les p-cycles FDPP soumis à des pannes multiples. Le nouveau modèle soulève un problème de taille, qui a un nombre exponentiel de contraintes en raison de certaines contraintes d’élimination de sous-tour. Par conséquent, afin de résoudre efficacement ce problème, on examine : (i) une décomposition hiérarchique du problème auxiliaire dans le modèle de décomposition, (ii) des heuristiques pour gérer efficacement le grand nombre de contraintes. À propos de la protection dans les réseaux multidomaines, nous proposons des systèmes de protection contre les pannes d’un lien. Tout d’abord, un modèle d’optimisation est proposé pour un système de protection centralisée, en supposant que la gestion du réseau soit au courant de tous les détails des topologies physiques des domaines. Nous proposons ensuite un modèle distribué de l’optimisation de la protection dans les réseaux optiques multidomaines, une formulation beaucoup plus réaliste car elle est basée sur l’hypothèse d’une gestion de réseau distribué. Ensuite, nous ajoutons une bande pasiv sante partagée afin de réduire le coût de la protection. Plus précisément, la bande passante de chaque lien intra-domaine est partagée entre les p-cycles FIPP et les p-cycles dans une première étude, puis entre les chemins pour lien/chemin de protection dans une deuxième étude. Enfin, nous recommandons des stratégies parallèles aux solutions de grands réseaux optiques multidomaines. Les résultats de l’étude permettent d’élaborer une conception efficace d’un système de protection pour un très large réseau multidomaine (45 domaines), le plus large examiné dans la littérature, avec un système à la fois centralisé et distribué.

Reinforcement Learning Approaches to Power System Scheduling

One major component of power system operation is generation scheduling. The objective of the work is to develop efficient control strategies to the power scheduling problems through Reinforcement Learning approaches. The three important active power scheduling problems are Unit Commitment, Economic Dispatch and Automatic Generation Control. Numerical solution methods proposed for solution of power scheduling are insufficient in handling large and complex systems. Soft Computing methods like Simulated Annealing, Evolutionary Programming etc., are efficient in handling complex cost functions, but find limitation in handling stochastic data existing in a practical system. Also the learning steps are to be repeated for each load demand which increases the computation time.Reinforcement Learning (RL) is a method of learning through interactions with environment. The main advantage of this approach is it does not require a precise mathematical formulation. It can learn either by interacting with the environment or interacting with a simulation model. Several optimization and control problems have been solved through Reinforcement Learning approach. The application of Reinforcement Learning in the field of Power system has been a few. The objective is to introduce and extend Reinforcement Learning approaches for the active power scheduling problems in an implementable manner. The main objectives can be enumerated as:(i) Evolve Reinforcement Learning based solutions to the Unit Commitment Problem.(ii) Find suitable solution strategies through Reinforcement Learning approach for Economic Dispatch. (iii) Extend the Reinforcement Learning solution to Automatic Generation Control with a different perspective. (iv) Check the suitability of the scheduling solutions to one of the existing power systems.First part of the thesis is concerned with the Reinforcement Learning approach to Unit Commitment problem. Unit Commitment Problem is formulated as a multi stage decision process. Q learning solution is developed to obtain the optimwn commitment schedule. Method of state aggregation is used to formulate an efficient solution considering the minimwn up time I down time constraints. The performance of the algorithms are evaluated for different systems and compared with other stochastic methods like Genetic Algorithm.Second stage of the work is concerned with solving Economic Dispatch problem. A simple and straight forward decision making strategy is first proposed in the Learning Automata algorithm. Then to solve the scheduling task of systems with large number of generating units, the problem is formulated as a multi stage decision making task. The solution obtained is extended in order to incorporate the transmission losses in the system. To make the Reinforcement Learning solution more efficient and to handle continuous state space, a fimction approximation strategy is proposed. The performance of the developed algorithms are tested for several standard test cases. Proposed method is compared with other recent methods like Partition Approach Algorithm, Simulated Annealing etc.As the final step of implementing the active power control loops in power system, Automatic Generation Control is also taken into consideration.Reinforcement Learning has already been applied to solve Automatic Generation Control loop. The RL solution is extended to take up the approach of common frequency for all the interconnected areas, more similar to practical systems. Performance of the RL controller is also compared with that of the conventional integral controller.In order to prove the suitability of the proposed methods to practical systems, second plant ofNeyveli Thennal Power Station (NTPS IT) is taken for case study. The perfonnance of the Reinforcement Learning solution is found to be better than the other existing methods, which provide the promising step towards RL based control schemes for practical power industry.Reinforcement Learning is applied to solve the scheduling problems in the power industry and found to give satisfactory perfonnance. Proposed solution provides a scope for getting more profit as the economic schedule is obtained instantaneously. Since Reinforcement Learning method can take the stochastic cost data obtained time to time from a plant, it gives an implementable method. As a further step, with suitable methods to interface with on line data, economic scheduling can be achieved instantaneously in a generation control center. Also power scheduling of systems with different sources such as hydro, thermal etc. can be looked into and Reinforcement Learning solutions can be achieved.

A User-Centric Perspective on Parallel Programming with Focus on OpenMP

The process of developing software that takes advantage of multiple processors is commonly referred to as parallel programming. For various reasons, this process is much harder than the sequential case. For decades, parallel programming has been a problem for a small niche only: engineers working on parallelizing mostly numerical applications in High Performance Computing. This has changed with the advent of multi-core processors in mainstream computer architectures. Parallel programming in our days becomes a problem for a much larger group of developers. The main objective of this thesis was to find ways to make parallel programming easier for them. Different aims were identified in order to reach the objective: research the state of the art of parallel programming today, improve the education of software developers about the topic, and provide programmers with powerful abstractions to make their work easier. To reach these aims, several key steps were taken. To start with, a survey was conducted among parallel programmers to find out about the state of the art. More than 250 people participated, yielding results about the parallel programming systems and languages in use, as well as about common problems with these systems. Furthermore, a study was conducted in university classes on parallel programming. It resulted in a list of frequently made mistakes that were analyzed and used to create a programmers' checklist to avoid them in the future. For programmers' education, an online resource was setup to collect experiences and knowledge in the field of parallel programming - called the Parawiki. Another key step in this direction was the creation of the Thinking Parallel weblog, where more than 50.000 readers to date have read essays on the topic. For the third aim (powerful abstractions), it was decided to concentrate on one parallel programming system: OpenMP. Its ease of use and high level of abstraction were the most important reasons for this decision. Two different research directions were pursued. The first one resulted in a parallel library called AthenaMP. It contains so-called generic components, derived from design patterns for parallel programming. These include functionality to enhance the locks provided by OpenMP, to perform operations on large amounts of data (data-parallel programming), and to enable the implementation of irregular algorithms using task pools. AthenaMP itself serves a triple role: the components are well-documented and can be used directly in programs, it enables developers to study the source code and learn from it, and it is possible for compiler writers to use it as a testing ground for their OpenMP compilers. The second research direction was targeted at changing the OpenMP specification to make the system more powerful. The main contributions here were a proposal to enable thread-cancellation and a proposal to avoid busy waiting. Both were implemented in a research compiler, shown to be useful in example applications, and proposed to the OpenMP Language Committee.

Evolving Distributed Algorithms with Genetic Programming

Distributed systems are one of the most vital components of the economy. The most prominent example is probably the internet, a constituent element of our knowledge society. During the recent years, the number of novel network types has steadily increased. Amongst others, sensor networks, distributed systems composed of tiny computational devices with scarce resources, have emerged. The further development and heterogeneous connection of such systems imposes new requirements on the software development process. Mobile and wireless networks, for instance, have to organize themselves autonomously and must be able to react to changes in the environment and to failing nodes alike. Researching new approaches for the design of distributed algorithms may lead to methods with which these requirements can be met efficiently. In this thesis, one such method is developed, tested, and discussed in respect of its practical utility. Our new design approach for distributed algorithms is based on Genetic Programming, a member of the family of evolutionary algorithms. Evolutionary algorithms are metaheuristic optimization methods which copy principles from natural evolution. They use a population of solution candidates which they try to refine step by step in order to attain optimal values for predefined objective functions. The synthesis of an algorithm with our approach starts with an analysis step in which the wanted global behavior of the distributed system is specified. From this specification, objective functions are derived which steer a Genetic Programming process where the solution candidates are distributed programs. The objective functions rate how close these programs approximate the goal behavior in multiple randomized network simulations. The evolutionary process step by step selects the most promising solution candidates and modifies and combines them with mutation and crossover operators. This way, a description of the global behavior of a distributed system is translated automatically to programs which, if executed locally on the nodes of the system, exhibit this behavior. In our work, we test six different ways for representing distributed programs, comprising adaptations and extensions of well-known Genetic Programming methods (SGP, eSGP, and LGP), one bio-inspired approach (Fraglets), and two new program representations called Rule-based Genetic Programming (RBGP, eRBGP) designed by us. We breed programs in these representations for three well-known example problems in distributed systems: election algorithms, the distributed mutual exclusion at a critical section, and the distributed computation of the greatest common divisor of a set of numbers. Synthesizing distributed programs the evolutionary way does not necessarily lead to the envisaged results. In a detailed analysis, we discuss the problematic features which make this form of Genetic Programming particularly hard. The two Rule-based Genetic Programming approaches have been developed especially in order to mitigate these difficulties. In our experiments, at least one of them (eRBGP) turned out to be a very efficient approach and in most cases, was superior to the other representations.

Sex differences in the programming effects of prenatal stress on psychopathology and stress responses: an evolutionary perspective

There is strong evidence from animal studies that prenatal stress has different effects on male and female offspring. In general, although not always, prenatal stress increases anxiety, depression and stress responses, both hypothalamic–pituitary–adrenal and cardiovascular, in female offspring rather than in male. Males are more likely to show learning and memory deficits. There have been few studies so far in humans which differentiate effects of prenatal stress on male and female psychopathology. Some studies support the animal models, but the evidence is inconsistent. The mediating mechanisms for any sex specific effects are little understood, but there is evidence that placental function can differ depending on the sex of the fetus. We suggest that there may be an evolutionary reason for any sex differences in the long term effects of prenatal stress. In a stressful environment it may be adaptive for females, who are more likely to stay in one place and look after children, to be more vigilant, alert to danger and thus show more stress responsiveness. This can give rise to a more anxious or depressed phenotype. With males it may be more adaptive to go out and explore new environments, compete with other males, and be more aggressive. For this it may help to be less responsive to external stressors. More research is needed into sex differences in the effects of prenatal stress in humans, to test these ideas.