<p>As document searching becomes more and more important with the rapid growth of document bases today, document clustering also becomes more important. Some of the most commonly used document clustering algorithms today, are pure statistical in nature. Other algorithms have emerged, adressing some of the issues with numerical algorithms, claiming to be better. This thesis compares two well-known algorithms: Elliptic K-Means and Suffix Tree Clustering. They are compared in speed and quality, and it is shown that Elliptic K-Means performs better in speed, while Suffix Tree Clustering (STC) performs better in quality. It is further shown that STC performs better using small portions of relevant text (snippets) on real web-data compared to the full document. It is also shown that a threshold value for base cluster merging is unneccesary. As STC is shown to perform adequately in speed when running on snippets only, it is concluded that STC is the better algorithm for the purpose of search results clustering.</p>

<p>In recent years, artificial development has been introduced to evolutionary algorithms as a means to overcome the scalability problem. Though in its early stages, it has been showing a lot of promise. Many studies have been conducted to improve our understanding of this methodology. Though many has been successful, there have been contradicting results. Further studies have been difficult because the results were obtained using not only different models, but on different platforms as well. Any comparison at this point will be full of uncertainties simply because there are too many factors to consider. I wish to contribute to the field of artificial development with this thesis. However, there will be no comparisons of various development models, or invention of a new model. I will leave these types tasks to better people. Instead, a platform to build development models will be introduced. The purpose of this platform will be made clear in course of the thesis. Two prominent models will be picked out to be ported to this platform, and it will be shown that not only is it possible to re-implement these models, it is also possible to reproduce the results. This feat will demonstrate the flexibility of the framework as well the benefits of using it.</p>

<p>A Data-intensive Approach to Prediction of Unwanted Events during Oil and Gas Well Drilling</p>

<p>This thesis presents a computational model of the basal ganglia that is able to learn sequences and perform action selection. The basal ganglia is a set of structures in the human brain involved in everything from action selection to reinforcement learning, inspiring research in psychology, neuroscience and computer science. Two temporal difference models of the basal ganglia based on previous work have been reimplemented. Several experiments and analyses help understand and describe the original works. This uncovered flaws and problems that is addressed.</p>

<p>The general purpose of this research is to investigate the possibilities offered for the use of Artificial Intelligence theory and methods in advanced game environments. The real-time strategy (RTS) game genre is investigated in detail, and an architecture and solutions to some common issues are presented. An RTS AI controlled opponent named “KAI” is implemented for the “TA Spring” game engine in order to advance the state of the art in usin AI techniques in games and to gain some insight into the strengths and weaknesses of AI Controlled Player (AI CP) architectures. A goal was to create an AI with behavior that gave the impression of intelligence to the human player, by taking on certain aspects of the style in which human players play the game. Another goal for the benefit of the TA Spring development community was to create an AI which played with sufficient skill to provide experienced players with resistance, without using obvious means of cheating such as getting free resources or military assets. Several common techniques were used, among others Rule-based decision making, path planning and path replanning, influence maps, and a variant of the A* search algorithm was used for searches of various kinds. The AI also has an approach to micromanagement of units that are fighting in combination with influence maps. The AI CP program was repeatedly tested against human players and other AI CP programs in various settings throughout development. The availability of testing by the community but the sometimes sketchy feedback lead to the production of consistent behavior for tester and developer alike in order to progress. One obstacle that was met was that the rule-based approach to combat behavior resulted in high complexity. The architecture of the RTS AI CP is designed to emerge a strategy from separate agents that were situation aware. Both the actions of the enemy and the properties of the environment are taken into account. The overall approach is to strengthen the AI CP through better economic and military decisions. Micromanagement and frequent updates for moving units is an important part of improving military decisions in this architecture. This thesis goes into the topics of RTS strategies, tactics, economic decisions and military decisions and how they may be made by AI in an informed way. Direct attempts at calculation and prediction rather than having the AI learn from experience resulted in behavior that was superior to most AI CPs and many human players without a learning period. However, having support for all of the game types for TA Spring resulted in extra development time. Keywords: computer science information technology RTS real time strategy game artificial intelligence architecture emergent strategy emergence humanlike behavior situation situational aware awareness combat behavior micro micromanagement pathfinder pathfinding path planning replanning influence maps threat DPS iterative algorithm algorithms defense placement terrain analysis attack defense military control artificial intelligence controlled player computer opponent game games gaming environmental awareness autonomous action actions agent hierarchy KAI TA Spring Total Annihilation</p>

<p>In this thesis we have investigated what concepts are and how they may be represented. We have seen that conceptual representations can be achieved by employing distributed representations in a hidden layer of a neural net- work. A pattern of activity is in this respect a conceptualization while the concept(s) it belongs to is a region of space treated alike by similarity based generalization. That is, the conceptualization may still have its individual properties only attributed to itself, but the properties relevant to the concept are shared among the representations in that region of space. These regions of space are allocated as dictated by coherently covarying properties of the domain, and thus constitutes a hierarchical representation of it. In this hier- archical representation, the most general concepts occupy the largest amount of space, with their subordinate concepts distributed in clusters allocated inside this space. This hierarchic representation is discovered in a coarse to fine manner, mirroring the conceptual development of a child. Properties being highly typical for a concept are, however, easier to learn and may thus be acquired before properties of concepts superordinate to them, mirroring basic level advantages in lexical acquisition. These typical properties show a higher level of activation throughout training. Frequency of presentation also influences how easy a concept or pattern is to acquire. Frequency of presentation causes a higher pressure to differentiate the instance, thus allo- cating a larger amount of space to it. This in turn facilitates the learning of its individual properties, thus attenuating the basic level advantages. The properties that covary coherently in the domain becomes more salient than other properties. This allows concepts to be acquired based on especially in- formative properties, thus possibly overlooking perceptual similarity. When noise was introduced into the system, the hierarchy broke down in a fine to coarse manner. These effects are all due to similarity based generalization and the coarse to fine differentiation of conceptual distinctions, and support many findings in semantic cognition. PDP thus serve as a good starting place for achieving conceptual representations. By viewing concepts as simulators (Barsalou, 1999; Barsalou, 2003a; Barsalou, 2003b), they are a skill to produce context-specific representations. This is also true of the hidden layer conceptual representations, although depending on whether the context is predictive. A simulator is comprised by a set of modality specific perceptual symbols extracted from perceptual states. Barsalou (1999) also offered valuable insights as to how simulators can support productivity and abstract thought. We have also seen how categorization can influence perceptual discrim- ination (Goldstone, 1994). By acquiring categories, the category relevant boundaries acquire distinctiveness with emphasis on the category boundary. For separable dimensions, the irrelevant dimension may receive acquired acquired similarity, however, one null effect was also found in (Goldstone, 60 1994). For Integral dimensions, the irrelevant dimension also acquired dis- tinctiveness. When two dimensions were relevant for categorization, the separable dimensions competed with each other, while the integral did not. Based on results from (Gluck & Meyers, 1993) I have proposed that a predic- tive auto-encoder can account for the results found for separable dimensions. During categorization learning, the stimuli along with the assigned category is processed by a predictive auto-encoder. The result is that predictive dimensions acquire distinctiveness while redundant ones acquire similarity. Whether or not the irrelevant dimension acquire similarity will thus depend on whether it has previously been predictive. Language is another factor influencing perceptual discrimination. When language was introduced into the system it had a profound influence on the conceptual representations (Cangelosi & Parisi, 2001). The representations acquired within category similarity and between category distinctiveness. The effect was largest for verbs, but was also present during non-linguistic processing. Language thus helped the network perfect its conceptual skills with respect to non-linguistic behavior. In Cangelosi & Riga (2006) language was used to implement grounding transfer. This is a process where new behavior is acquired by grounding it in previously learned behavior. This was achieved in the guid- ance of language. This could also be seen as an implementation of Barsalou’s (1999) productivity mechanism. The involvement of language in simulating abstract thought has also been discussed. With reference to cangelosi & Parisi (2001) and Cangelosi & Riga (2006) it seems that language has a profound effect on conceptual processing. Dimensionality of the representation is another important factor in con- ceptual representations. As the dimensionality increases, the number of examples necessary to reach a given level of performance increases exponen- tially (Edelman & Intrator, 1997). Auto-encoders is a common method for unsupervised dimensionality reductions which also preserves the topology of the original domain. The dimensionality is reduced by compressing redun- dant information thus allowing conception to focus on the relevant aspect of the representation. We have also reviewed a theory if prefrontal cortex function suggesting its implication in guiding computation along processing specific pathways and also in acquiring categories and rules (Miller & Freedman, et. al., 2002; Miller & Cohen, 2001; Braver & Cohen, 2000). The PFC thus seems es- sential in conception. However, as the rules learned in the PFC is executed frequently, they get “pushed” down to more autonomous areas of the brain and thus become more autonomous. The PFC will thus be most involved in behavior requiring attention, among which acquiring concepts certainly belongs. A framework for higher level cognitive behavior from Veflingstad & Yildirim (2007) was introduced. This framework was introduced within three levels of cognition: the stimulus-resonse level, the conceptual level 61 and the language level. Within this framework it is proposed that algo- rithms exist in the brain and that they are represented non-symbolically at the conceptual level. They operate on non-symbolic concepts and makes decisions using feed forward networks modeling an if-then rule. By em- ploying distributed representations these algorithms exhibit the properties we have this far discussed and will thus exhibit semantic task performance. These algorithms help experiencing more complex thought and are engaged in higher level cognitive tasks such as planning. A simulation of a non- symbolic summation algorithm was presented showing the feasibility of the approach. It was proposed that the PFC is in charge of learning these algo- rithms, but as they are frequently executed they get “pushed” down to more autonomous areas of the brain and thus no longer require as much attention to be executed. Novelty was proposed as a means of autonomous exploration and a con- tinuous “type checking” parameter. Novelty is an informative and important “signal” as it allows one to assess knowledge of a perceived instance without any explicit reference of memory. This was implemented in a simulation as the sum of differences between the input pattern and the output pattern of an auto-encoder. The simulation showed that novelty could be reliably as- sessed within and between modalities as long as the environment was noise free. When noise was introduced, the performance dropped. The simula- tion was, however, very constrained as the link between the modalities only supported “one to one” relationships. It was therefor suggested that novelty of associations was better assessed as the amount of selective attention the PFC must exert in order for a pattern of activity in a massively recurrent system to settle into a new attractor. It should be mentioned that novelty is here interpreted very broadly. It might be possible that a specific association has been observed many times but that some other association overrides it in the system. This association would thus not be novel in that it has not been experienced but in that it has not been learned to a sufficient degree. Novelty is here also used as an assessment of which of two associations are least familiar. Novelty in this respect would thus be a measure of the amount of stress a current line of processing introduces in the system. From the material presented in this thesis I will in line with Barsalou (2003b) conclude that the concept arises from a skill for producing context- specific representations. This skill arises from interacting with the world and observing meaningful relationships and properties within it. As this skill improves, perception is affected in a way further facilitating this skill. Once this skill has reached a certain level, language can be acquired, improving this skill even more. This in turn, probably facilitates further acquisition of language. Within reference to the three levels proposed there seems to be a circular dependency between the layers with the concept arising from this interaction. However, since conception can arise simply by similarity based generalization, language would not seem necessary for conception. It 62 does seem important in the complex conceptual abilities to humans though. Even though it is here concluded that the concept emerges from the skill of the system, this does not mean that it can not be investigated as patterns of activation. As wee have seen, much can be learned from these patterns. They can also be employed in algorithms achieving more complex thought.</p>

<p>Cognitive vision is an interesting field of research that tries to create vision systems with cognitive abilities. Automated video surveillance is increasingly needed to watch our public transport systems, either as a totally automated system or as an operator assistant. In this thesis a design for a cognitive automated video surveillance system is proposed. A hybrid ANN/CBR behavior analysis system is proposed as a cognitive extension of existing video tracking system, and a prototype is developed. By investigating the current state of cognitive vision and automated video surveillance and by looking at existing hybrid approaches to combine them, it is argued that this approach is an area of research where few designs are implemented and tested. Several frameworks for both ANN/CBR hybrids are proposed in literature, and so called emergent cognitive system frameworks are also presented, but few implementations have been done. As far as our literature review has spanned, no automated video surveillance system is attempted with the use of an ANN/CBR hybrid.</p>

<p>This thesis presents a further development of Neuroevolution of Augmenting topologies(NEAT)[21]. The author augments NEAT by parallelizing the fitness evaluation of the phenotypes enabling the method to be utilized on highly complex fitness evaluations by running it on a cluster. This augmented version of NEAT is then applied to the inherently complex problem of the Go board game, by using the Gnugo (See www.gnu.org/software/gnugo/.) software package as a fitness evaluator. The performance increase also enables the author to follow up on the predictions of Kenneth Stanley’s previous discussions that co-evolution will help evolve a more general Go player, rather than the predicted evolved behaviour of specializing in beating Gnugo.</p>

<p>Robotic mapping systems are traditionally separated into the metric and the topological paradigm. The metric approach provides geometrical accuracy, but is fragile because it is bounded in an absolute coordinate system and depends on the use of odometry for navigation. The topological paradigm provides a compact presentation and navigation free of accumulated error. In this thesis the topological and the metric paradigm is combined into a hybrid representation where a topological map joins a set of local maps. Each local map contains a pair of self-organizing maps, one that maps the metric space of the local map, and one that maps the perceptual space of the local map. Local navigation is performed over the SOM mapping the metric space and position correction is performed over the SOM mapping the perceptual space. A boundary-tracing behavior is used for navigation within the global map, while the local metric maps allow for more precise navigation and is navigated by performing path-integration.</p>

<p>Conventional artificial neural networks have traditionally faced inherent problems with efficient parallelization of neuron processing. Recent research has shown how artificial spiking neural networks can, with the introduction of biologically plausible synaptic conduction delays, be fully parallelized regardless of their network topology. This, in conjunction with the influx of fast, massively parallel desktop-level computing hardware leaves the field of efficient, large-scale spiking neural network simulations potentially open to even those with no access to supercomputers or large computing clusters. This thesis aims to show how such a parallelization is possible as well as present a network model that enables it. This model will then be used as a base for implementing a parallel artificial spiking neural network on both the CPU and the GPU and subsequently evaluating some of the challenges involved, the performance and scalability measured and the potential that is exhibited.</p>