<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>

<p>This master's thesis has investigated how methods from artificial intelligence (AI) can be used to perform and augment production optimization of sub-sea oil reservoirs. The methods involved in this work are genetic algorithms (GAs) and artificial neural networks (ANNs). Different optimization schemes were developed by the author to perform production optimization on oil reservoir simulator models. The optimization involves finding good input parameter values for certain properties of the model, relating to how the wells in the oil reservoir operate. The research involves straightforward optimization using GAs, model approximations using ANNs, and also more advanced schemes using these methods together with other available technology to perform and augment reservoir optimization. With this work, the author has attempted to make a genuine contribution to all the research areas this master's thesis has touched upon, ranging from computer science and AI to process and petroleum engineering. The methods and approaches developed through this research were compared to the performance of each other and also to other approaches and methods used on the same challenges. The comparison found some of the developed optimization schemes to be very successful, while others were found to be less appropriate for solving the problem at hand. Some of the less successful approaches still showed considerable promise for simpler problems, leading the author to conclude that the developed schemes are suited for solving optimization problems in the petroleum industry.</p>

The buckling of compressively-loaded members is one of the most important factors limiting the overall strength and stability of a structure. I have developed novel techniques for using active control to wiggle a structural element in such a way that buckling is prevented. I present the results of analysis, simulation, and experimentation to show that buckling can be prevented through computer-controlled adjustment of dynamical behavior.sI have constructed a small-scale railroad-style truss bridge that contains compressive members that actively resist buckling through the use of piezo-electric actuators. I have also constructed a prototype actively controlled column in which the control forces are applied by tendons, as well as a composite steel column that incorporates piezo-ceramic actuators that are used to counteract buckling. Active control of buckling allows this composite column to support 5.6 times more load than would otherwise be possible.sThese techniques promise to lead to intelligent physical structures that are both stronger and lighter than would otherwise be possible.

These proceedings summarize the results of the First PHANToM User's Group Workshop held September 27-30, 1996 MIT. The goal of the workshop was to bring together a group of active users of the PHANToM Haptic Interface to discuss the scientific and engineering challenges involved in bringing haptics into widespread use, and to explore the future possibilities of this exciting technology. With over 50 attendees and 25 presentations the workshop provided the first large forum for users of a common haptic interface to share results and engage in collaborative discussions. Short papers from the presenters are contained herein and address the following topics: Research Effort Overviews, Displays and Effects, Applications in Teleoperation and Training, Tools for Simulated Worlds and, Data Visualization.

When triangulating a belief network we aim to obtain a junction tree of minimum state space. Searching for the optimal triangulation can be cast as a search over all the permutations of the network's vaeriables. Our approach is to embed the discrete set of permutations in a convex continuous domain D. By suitably extending the cost function over D and solving the continous nonlinear optimization task we hope to obtain a good triangulation with respect to the aformentioned cost. In this paper we introduce an upper bound to the total junction tree weight as the cost function. The appropriatedness of this choice is discussed and explored by simulations. Then we present two ways of embedding the new objective function into continuous domains and show that they perform well compared to the best known heuristic.

In previous work (Olshausen & Field 1996), an algorithm was described for learning linear sparse codes which, when trained on natural images, produces a set of basis functions that are spatially localized, oriented, and bandpass (i.e., wavelet-like). This note shows how the algorithm may be interpreted within a maximum-likelihood framework. Several useful insights emerge from this connection: it makes explicit the relation to statistical independence (i.e., factorial coding), it shows a formal relationship to the algorithm of Bell and Sejnowski (1995), and it suggests how to adapt parameters that were previously fixed.