Artificiella neurala nätverk (ANN) har många användningsområden inom datavetenskap. Några av dessa är mönsterigenkänning, robotik, processkontroll, optimering och spel. Detta examensarbete kommer att handla om hur en alternativ lösning på den traditionella arkitekturen av hur ett neuralnät kan se ut. Jag kommer att undersöka om man kan ta ett stort och komplext neuralnät och bryta ned detta till mindre neuralnät utan att förlora kvaliteten på botarna i en spelmiljö kallad Open Nero. Detta för att försöka minska beräkningshastigheten av neuralnäten och förhoppningsvis även göra så botarna lär sig ett bra beteende snabbare. Mitt examensarbete kommer att visa att min lösning av arkitekturen för ett neuralt nätverk inte fungerar speciellt bra då botarna inte lärde sig tillräckligt fort.

Since the mid 60?s, Germany has seen dropping fertility rates and yet next to nothinghas been done to combat this trend until the current regime led by Angela Merkel andher minister of family affairs, Ursula von der Leyen initiated a number ofcomprehensive reforms of Germany?s family policies.Family policy in Germany is being reformed in three ways. First of all parents arenow eligible to receive substantial financial support in order to compensate the loss ofincome associated with a pregnancy and or parental leave. Second, the all but nonexistentpublic child care services are being vastly expanded with the goal of beingable to offer child care service for every child age 0-3. Thirdly the tradition of schoolsending classes midday is being reformed with the aim of letting kids stay in schoolmuch longer thus enabling parents to work full-time as opposed to part-time in orderto be able to take care of kids returning from school.The hopes for these ambitious reforms are tremendous.

Denna rapport jämför prestandan mellan state-of-the-art AI-botar i racing spelet TORCS och en AI-bot som kör med hjälp av ett artificiellt neuralt nätverk (ANN-bot). ANN-boten, som implementerades som en del av arbetet, använder en feedforward arkitektur och backpropagation för inlärning. Ett separat program som användes för att träna det neurala nätverket med träningdata som spelats in från TORCS implementerades också. Som state-of-the-art AI-botar användes AI-botar som har använts i en tävling. De fyra AI-botarna testades på åtta olika banor och data om hur lång tid varje varv tog och hur snabbt AI-botarna körde sparades och sammanställdes.

"Infiltration of Waldheim" är ett spel gjort av David Lindell (grafik), Andreas Persson (programmering) och Mathias Jönsson (ljud och musik). Målet vi hade med projektet var att ha en spelbar bana med minst en vapen typ samt fiender att eliminera, allt ackompanjerat med pampig musik och en massa ljudeffekter. Jag kommer i denna rapport beskriva arbetets gång samt reflektera över vad som har fungerat och vad som varit mindre bra under projektets gång. Mina planer för spelet var mest att lära mig mera om framförallt AI samt arbeta mera i 3d. Spelet ska mest vara för mig själv, men med lite putsning och mera innehåll eventuellt användas vid jobb ansökningar i framtiden..

Modern air battles are very dynamic and fast, and put extreme pressure on pilots. In some unpredictable situations, like new discovered threats or mission plan deviation because of enemy aircraft, the pilots might need to replan their predefined flight route. This is very difficult, if not impossible, to do since numerous factors affect it. A system that can help the pilots to do such a thing is needed. Previous work in this field has involved methods from artificial intelligence like A*-search.

Health and fitness are two controversial and not easily defined topics that affect people in our modern society every day. We believe that we can find a link between individualism, globalization and the stress concerning weight and appearance ideals. Our bodies have turned into a popular subject for the media, and there is no indication that the interest will decline. As the world gets more artificial, "natural" ideals are getting more attention, such as the concept of a strong and healthy body. But there is also a downside, for example with health issues such as cardiovascular disease increasing following the birth of high-fat diets.

Research show evidence for benefits of breastfeeding and that infant-feeding-plans are supportive. Family-centered care is the theoretical framework. Family support is crucial for successful breastfeeding. It is important that society creates opportunities for mothers to breastfeed and contribute information and support by healthcare professionals. The aim of this study was to evaluate how the midwives and child healthcare nurses found that the newest breastfeeding strategy influenced their breastfeeding- and rearing support in the County of Jönköping.

This paper examines possible applications of fuzzy logic on the field of artificial intelligence in digital games. It describes fuzzy logic in contrast to crisp logic. The paper will give several examples of possible applications of fuzzy logic-based decision making for game AI. These examples include the choosing of weapons for AI agents and the gas-break decision of an AI-controlled car. The paper will also analyze the impacts of game AI which makes decisions based on many factors.

AbstractThe purpose of this bachelor thesis is to describe the use of artificial insemination (AI) in sheep and discuss the possibilities for AI in Sweden. Male and female fertility, heat detection, semen handling and insemination techniques in sheep are described. Advantages and disadvantages of AI are discussed. In order to achieve genetic progress it is important with well planned and implemented breeding programs. The Swedish Sheep Recording Scheme and computer software from Elitlamm are the basis for sheep breeding in Sweden.

As artificial intelligence (AI) has gained more influence in recruitment, both recruitment processes and the role of the recruiter are changing. This study aims to describe and analyze how recruiters translate, use, and relate to AI in their work. Through a qualitative method based on semi-structured interviews and document analysis, the study explores recruiters? experiences, attitudes, as well as perceived obstacles and opportunities regarding the use of AI in recruitment. With a theoretical foundation in translation theory, fashion, and imitation, the study examines how AI is not only followed as a trend, but also shaped and adapted locally through translation, depending on organizational identity and needs.

In order to investigate if the KRAV-regulations have any effects on the health and welfare of calves, KRAV-affiliated farms were compared to conventional farms with respect to calf management and outcome. The dairy calf has had a low economical impact during history. Even today the value of the calf is low and a lot of calves have a poor health status. The calf breeding is built on tradition and on the fact, that cheap antibiotics have made it possible to ignore, the recommendations about good hygiene in the calf?s environment.

Dairy farmers using artificial insemination (AI) are dependent on effective oestrus detection. In Sweden, AI is used for a majority of all dairy cows and oestrus synchronisation with hormones is not allowed. There are reports of declining ability to express oestrus with higher levels of milk production. This makes oestrus detection more difficult. Several aids for oestrus detection have been developed, for instance pedometers and mounting detectors.

In the curriculum for Swedish pre-school the focus is mainly on five concepts. These are care of the children, learning, influence, rearing and security. These concepts are to characterize the activities of the pre-school in Sweden.Back in time the focal point of pre-school activities for young children was mainly on security. The learning part became more prominent as the children grew older. When speaking to teachers and parents I do sense that some believe this is the case even nowadays.

This thesis presents the implementation of a knowledge base system for rough sets [Paw92]within the logic programming framework. The combination of rough set theory with logic programming is a novel approach. The presented implementation serves as a prototype system for the ideas presented in [VDM03a, VDM03b]. The system is available at "http://www.ida.liu.se/rkbs". The presented language for describing knowledge in the rough knowledge base caters for implicit definition of rough sets by combining different regions (e.g.

Den klassiska approachen till navigering innefattar att agenten håller en intern representativ modell av omgivningen. Denna approach har emellertid många nackdelar, speciellt för dynamiska miljöer. En modernare approach är att förlita sig på den faktiska omgivningen istället för en modell av denna. Detta arbete presenterar en undersökning av navigeringsproblemet och hur väl det löses av agenter vars kontrollmekanismer utgörs artificiella neurala nätverk. Tillförlitligheten hos de två neurala arkitekturerna Extended sequential cascaded network och Self-organized recurrent network bestäms genom experiment.