I detta arbete som fokuserar på hur neurala nätverk kan appliceras på och hur väl de presterar i en spelmiljö undersöks två nätverksarkitekturer applicerat på en simulation av ett så kallat urvalsbaserat spel. I arbetet så är ett urvalsbaserat spel ett spel som går ut på att en spelare skall göra en mängd val innan spelet börjar, och de två nätverksarkitekturerna som utvärderas är Feed Forward och NEAT. Experimenten låter nätverken skapa lag för en förenklad version av spelet Pokemon och kommer sedan att låta dessa lag tävla emot varandra i en deterministisk testmiljö för att bedöma hur bra nätverken presterar.

Context. Games are becoming larger and the amount of assets required is increasing. Game studios turn toward procedural generation to ease the load of asset creation. After the game is released the studios want to extend the longevity of their creation. One way of doing this is to open up the game for community created add-ons and assets or utilize some procedural content generation. Both community created assets and procedural generation comes with a classification problem to filter out the undesirable content. Objectives. This thesis will attempt to create a method to evaluate community-generated StarCraft maps with the help of machine learning. Methods. Manually extracted metrics from StarCraft maps and ratings from community repositories. This data is used to train neural networks using NeuroEvolution of Augmenting Topologies (NEAT). The method will be compared with Sequential Minimal Optimization (SMO) and ZeroR. Results and Conclusions. The problem turned out to be more difficult than initially thought. The results using NEAT are marginally better than SMO and ZeroR. The suspected reason for this is insufficient input data and/or bad input parameters. Further experimentation could be conducted with deep learning to try to find a suitable solution for this problem.

Neural Networks have been applied in numeral broad categories of work. Such as classification, data processing, robotics, systemcontrol e.t.c. This thesis compares using traditional methods of the routing process in chip circuit design to using a Neural Network trained with evolution. Constructing and evaluating a chip design is a complicated thing, where a lot of variables have to be accounted for and therefore a simplified evaluation and design process is used in order to train the network and compare the results. This was done by constructing simple test cases and running the algorithms BFS, A*Star and the neural network and comparing the paths each algorithm found using a fitness function. The results were that BFS and A*Star both performed better on complex circuits, but the neural network was able to create better paths on very small and niche circuits. The conclusion of the study is that the neural network approach is not able to compete with the standard industry methods of the routing process, but we do not exclude the possibility that with a better designed Fitness function, this could be possible. / Neurala Nätverk används i flertal breda kategorier av arbete. Såsom klassificering, databehandling, robotik, systemkontroll e.t.c. Denna avhandling jämför traditionella metoder för routingprocessen i chip-kretsdesign med att använda ett neuralt nätverk utbildat med evolution. Att konstruera och utvärdera en chipdesign är en komplicerad sak, där många variabler måste tas hänsyn till och därför används en förenklad utvärderings- och designprocess för att träna nätverket och jämföra resultaten. Detta gjordes genom att konstruera enkla testfall och köra algoritmerna BFS, A * Star och det neurala nätverket och jämföra de sökvägar som varje algoritm fann med hjälp av en så kallad Fitness-funktion. Resultaten var att BFS och A * Star både fungerade bättre på komplexa kretsar, men det neurala nätverket kunde skapa bättre vägar på mycket små och nischade kretsar. Slutsatsen av studien är att det neurala nätverkssättet inte kan konkurrera med routingprocessens standardindustrimetoder, men vi utesluter inte möjligheten att med en bättre utformad Fitness-funktion skulle detta vara möjligt.

Across many scientific disciplines, there has emerged an open opportunity to utilize the scale and reach of the Internet to collect scientific contributions from scientists and non-scientists alike. This process, called citizen science, has already shown great promise in the fields of biology and astronomy. Within the fields of artificial life (ALife) and evolutionary computation (EC) experiments in collaborative interactive evolution (CIE) have demonstrated the ability to collect thousands of experimental contributions from hundreds of users across the glob. However, such collaborative evolutionary systems can take nearly a year to build with a small team of researchers. This dissertation introduces a new developer framework enabling researchers to easily build fully persistent online collaborative experiments around almost any evolutionary domain, thereby reducing the time to create such systems to weeks for a single researcher. To add collaborative functionality to any potential domain, this framework, called Worldwide Infrastructure for Neuroevolution (WIN), exploits an important unifying principle among all evolutionary algorithms: regardless of the overall methods and parameters of the evolutionary experiment, every individual created has an explicit parent-child relationship, wherein one individual is considered the direct descendant of another. This principle alone is enough to capture and preserve the relationships and results for a wide variety of evolutionary experiments, while allowing multiple human users to meaningfully contribute. The WIN framework is first validated through two experimental domains, image evolution and a new two-dimensional virtual creature domain, Indirectly Encoded SodaRace (IESoR), that is shown to produce a visually diverse variety of ambulatory creatures. Finally, an Android application built with WIN, "filters, allows users to interactively evolve custom image effects to apply to personalized photographs, thereby introducing the first CIE application available for any mobile device. Together, these collaborative experiments and new mobile application establish a comprehensive new platform for evolutionary computation that can change how researchers design and conduct citizen science online.

Military, Medical, Exploratory, and Commercial robots have much to gain from exchanging wheels for legs. However, the equations of motion of dynamic bipedal walker models are highly coupled and non-linear, making the selection of an appropriate control scheme difficult. A temporal difference reinforcement learning method known as Q-learning develops complex control policies through environmental exploration and exploitation. As a proof of concept, Q-learning was applied through simulation to a benchmark single pendulum swing-up/balance task; the value function was first approximated with a look-up table, and then an artificial neural network. We then applied Evolutionary Function Approximation for Reinforcement Learning to effectively control the swing-leg and torso of a 3 degree of freedom active dynamic bipedal walker in simulation. The model began each episode in a stationary vertical configuration. At each time-step the learning agent was rewarded for horizontal hip displacement scaled by torso altitude--which promoted faster walking while maintaining an upright posture--and one of six coupled torque activations were applied through two first-order filters. Over the course of 23 generations, an approximation of the value function was evolved which enabled walking at an average speed of 0.36 m/s. The agent oscillated the torso forward then backward at each step, driving the walker forward for forty-two steps in thirty seconds without falling over. This work represents the foundation for improvements in anthropomorphic bipedal robots, exoskeleton mechanisms to assist in walking, and smart prosthetics. / Master of Science

Real-time strategy games are an exciting area of research, as creating a game AI poses many challenges - from managing a single unit to completing an objective of the game. This thesis explores possible solutions to this task, using genetic programming and neuroevolution. It presents and compares findings and differences between the models. Both methods performed reasonably well, but genetic programming was found to be a bit more effective in performance and results.

Gram-positive pathogenic bacteria utilize cell-surface anchored proteins to bind and transport heme into the cell. These bacteria acquire iron from host proteins containing heme e.g., hemoglobin. Proteins like HmuT from Corynebacterium diphtheriae bind and help transport heme into the cell. Residues His136 and Tyr235 are utilized as the axial ligands, with a conserved Arg237 residue acting as the hydrogen bonding partner to the axial Tyr235. Similarly, Streptococcus pyogenes utilizes the cell anchored protein Shr to transfer heme into the cell. Shr-NEAT2 is hexacoordinated by two axial methionines and is prone to autoreduction where lysines are the most likely source of electrons. Lastly, PefR of Group A Streptococcus is a DNA transcription factor which regulates protein expression. Preliminary studies indicate a cysteine may coordinate the heme. A combination of UV-visible, resonance Raman, and magnetic circular dichroism spectroscopies shows these proteins play a crucial role heme transport and regulation.

The paper deals with extarnalities in transport, position of Switzerland in european freight and situation in alpine freight in overall. Analyzes instruments applied in the swiss Road to rail transfer politics, infrastructure charging, rail infrastructure projects and development of freight in swiss alpine tunnels since 1980. The paper briefly discuses possible solitions with overlap into future of swiss trafic management projects.

Tatueringskonsten är uråldrig och har präglats av negativa attityder och stigmatisering samt att forskning har visat att tatueringar påverkar tillskrivningen av egenskaper. Syftet med studien var att undersöka om tatueringar kan förstärka tillskrivningen av egenskaper när en individ anses vara vårdad eller ovårdad. Studien utfördes genom ett experiment där fyra versioner av bilder på en kvinna manipulerats utifrån resultatet av en pilotstudie som undersökte vårdadhet. Resultatet visade att tatueringar har en signifikant påverkan på tillskrivningen av positiva sociala egenskaper där kvinnan med tatueringar skattades högre än sin icke-tatuerade motpart. Tatueringar hade ingen effekt på indexen Utseende och Kompetens. Ingen interaktionseffekt mellan vårdadhet och tatueringar identifierades. Resultatet går i linje med forskning från de senaste tre åren och tyder på att bilden av tatuerade har förändrats. Förslag till framtida forskning är att replikera studien med starkare manipulation av variabeln vårdadhet samt studera tidigare undersökta områden för att verifiera attityden till tatuerade.

This work produced the retrofit of an air-fired, 150 kW reactor for oxy-combustion which was then used in three oxy-combustion studies: strategic oxy-combustion design, oxy-combustion of petroleum coke, and air versus oxy-combustion radiative heat flux measurements. The oxy-combustion retrofit was accomplished using a system of mass flow controllers and automated pressure switches which allowed safe and convenient operation. The system was used successfully in the three studies reported here and was also used in an unrelated study. A study was completed where a novel high oxygen participation burner was investigated for performance while burning coal related to flame stability, NO, and burnout using a burner supplied by Air Liquide. Parameters investigated included oxygen (O2) injection location, burner swirl number and secondary carbon dioxide (CO2) flow rate. The data showed swirl can be used to stabilize the flame while reducing NO and improving burnout. Center O2 injection helped to stabilize the flame but increased NO formation and decreased burnout by reducing particle residence time. Additional CO2 flow lifted the flame and increased NO but was beneficial for burnout. High O2 concentrations up to 100% in the secondary were accomplished without damage to the burner. Petroleum coke was successfully burned using the Air Liquide burner. Swirl of the secondary air and O2 injection into the center tube of the burner were needed to stabilize the flame. Trends in the data similar to those reported for the coal study are apparent. Axial total radiant intensity profiles were obtained for air combustion and three oxy-combustion operating conditions that used hot recycled flue gas in the secondary stream. The oxygen concentration of the oxidizer stream was increased from 25 to 35% O2 by decreasing the flow rate of recycled flue gas. The decrease in secondary flow rate decreased the secondary velocity, overall swirl, and mixing which elongated the flame. Changing from air to neat CO2 as the coal carrier gas also decreased premixing which elongated the flame. Flame elongation caused increased total heat transfer from the flame. The air flame was short and had a higher intensity near the burner, while high O2 concentration conditions produced lower intensities near the burner but higher intensities and temperatures farther downstream. It was shown that oxycombustion can change flame shape, temperature and soot concentration all influencing heat transfer. Differences in gas emission appear negligible in comparison to changes in particle emission.