Hedge fund performance is modeled from publically available data using feed-forward neural networks trained using a resilient backpropagation algorithm. The neural network’s performance is then compared with linear regression models. Additionally, a stepwise factor regression approach is introduced to reduce the number of inputs supplied to the models in order to increase precision. Three main conclusions are drawn: (1) neural networks effectively model hedge fund returns, illustrating the strong non-linear relationships between the economic risk factors and hedge fund performance, (2) while the group of 25risk factors we draw variables from are used to explain hedge fund performance, the best model performance is achieved using different subsets of the 25 risk factors, and, (3) out-of-sample model performance degrades across the time during the recent (and still on-going) financial crisis compared to less volatile time periods, indicating the models’ inability to predict severely volatile economic scenarios such as economic crises.

Hedge fund performance is modeled from publically available data using feed-forward neural networks trained using a resilient backpropagation algorithm. The neural network’s performance is then compared with linear regression models. Additionally, a stepwise factor regression approach is introduced to reduce the number of inputs supplied to the models in order to increase precision. Three main conclusions are drawn: (1) neural networks effectively model hedge fund returns, illustrating the strong non-linear relationships between the economic risk factors and hedge fund performance, (2) while the group of 25risk factors we draw variables from are used to explain hedge fund performance, the best model performance is achieved using different subsets of the 25 risk factors, and, (3) out-of-sample model performance degrades across the time during the recent (and still on-going) financial crisis compared to less volatile time periods, indicating the models’ inability to predict severely volatile economic scenarios such as economic crises.

The purpose of this thesis was to delineate the neural underpinning of three types of declarative memory retrieval; autobiographical, episodic, and semantic. Autobiographical memory was defined as the conscious recollection of personally relevant events, episodic memory as the recall of stimuli presented in the laboratory, and semantic memory as the retrieval of factual information and general knowledge about the world. Young adults participated in an event-related fMRI study in which pictorial stimuli were presented as cues for retrieval. By manipulating retrieval demands, autobiographical, episodic, or semantic memories were extracted in response to the same stimulus. The objective of the subsequent analyses was threefold: firstly, to delineate regional activations common across the memory conditions, as well as neural activations unique to each memory type (“condition-specific”); secondly, to delineate a functional network common to all three memory conditions; and, thirdly, to delineate functional network(s) of brain regions that show condition-specific activity and to assess their overlap with the common functional network. The results of the first analysis showed regional activations common to all three types of memory retrieval in the bilateral inferior frontal gyrus, left middle frontal gyrus, right caudate nucleus, bilateral thalamus, left hippocampus, and left lingual gyrus. Condition-specific activations were also delineated, including medial frontal increases for autobiographical, right middle frontal increases for episodic, and right inferior temporal increases for semantic retrieval. The second set of analyses delineated a functional network common to the three conditions that comprised 21 functionally connected neural areas. The final set of analyses further explored the functional connectivity of those brain regions that showed condition-specific activations, yielding two functional networks – one involved semantic and autobiographical conditions, and the other involved episodic and autobiographical conditions. Despite their recruiting some brain regions unique to the content of retrieved memories, the two functional networks did overlap to a degree with the common functional network. Together, these findings lend support to the notion of a common network, which is hypothesized to give rise to different types of declarative memory retrieval (i.e., autobiographical, episodic, or semantic) along a contextual continuum (i.e., highly contextualized or highly decontextualized).

In this work new artificial learning and innate control mechanisms are proposed for application in autonomous behavioral systems for mobile robots. An autonomous system (for mobile robots) existent in the literature is enhanced with respect to its capacity of exploring the environment and avoiding risky configurations (that lead to collisions with obstacles even after learning). The particular autonomous system is based on modular hierarchical neural networks. Initially,the autonomous system does not have any knowledge suitable for exploring the environment (and capture targets œ foraging). After a period of learning,the system generates efficientobstacle avoid ance and target seeking behaviors. Two particular deficiencies of the forme rautonomous system (tendency to generate unsuitable cyclic trajectories and ineffectiveness in risky configurations) are discussed and the new learning and controltechniques (applied to the autonomous system) are verified through simulations. It is shown the effectiveness of the proposals: theautonomous system is able to detect unsuitable behaviors (cyclic trajectories) and decrease their probability of appearance in the future and the number of collisions in risky situations is significantly decreased. Experiments also consider maze environments (with targets distant from each other) and dynamic environments (with moving objects).

Thesis (Ph. D.)--University of Washington, 2001. / Vita. Includes bibliographical references (leaves 59-63).

Thesis (Ph.D.)--York University, 2008. Graduate Programme in Applied Mathematics. / Typescript. Includes bibliographical references (leaves 225-239). Also available on the Internet. MODE OF ACCESS via web browser by entering the following URL: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&res_dat=xri:pqdiss&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&rft_dat=xri:pqdiss:NR46003

Thesis (Ph. D.)--University of Washington, 2003. / Vita. Includes bibliographical references (leaves 76-80).

Multiple-Input Multiple-Output (MIMO) systems have gained an enormous amount of attention as one of the most promising research areas in wireless communications. However, while MIMO systems have been extensively explored over the past decade, few schemes acknowledge the nonlinearity caused by the use of high power amplifiers (HPAs) in the communication chain. When HPAs operate near their saturation points, nonlinear distortions are introduced in the transmitted signals, and the resulting MIMO channel will be nonlinear. The nonlinear distortion is further exacerbated by the fading caused by the propagation channel. The goal of this thesis is: 1) to use neural networks (NNs) to model and identify nonlinear MIMO channels; and 2) to employ the proposed NN model in designing efficient detection techniques for these types of MIMO channels. In the first part of the thesis, we follow a previous work on modeling and identification of nonlinear MIMO channels, where it has been shown that a proposed block-oriented NN scheme allows not only good identification of the overall MIMO input-output transfer function but also good characterization of each component of the system. The proposed scheme employs an ordinary gradient descent based algorithm to update the NN weights during the learning process and it assumes only real-valued inputs. In this thesis, natural gradient (NG) descent is used for training the NN. Moreover, we derive an improved variation of the previously proposed NN scheme to avoid the input type restriction and allow for complex modulated inputs as well. We also investigate the scheme tracking capabilities of time-varying nonlinear MIMO channels. Simulation results show that NG descent learning significantly outperforms the ordinary gradient descent in terms of convergence speed, mean squared error (MSE) performance, and nonlinearity approximation. Moreover, the NG descent based NN provides better tracking capabilities than the previously proposed NN. The second part of the thesis focuses on signal detection. We propose a receiver that employs the neural network channel estimator (NNCE) proposed in part one, and uses the Zero-Forcing Vertical Bell Laboratories Layered Space-Time (ZF V-BLAST) detection algorithm to retrieve the transmitted signals. Computer simulations show that in slow time-varying environments the performance of our receiver is close to the ideal V-BLAST receiver in which the channel is perfectly known. We also present a NN based linearization technique for HPAs, which takes advantage of the channel information provided by the NNCE. Such linearization technique can be used for adaptive data predistortion at the transmitter side or adaptive nonlinear equalization at the receiver side. Simulation results show that, when higher modulation schemes (>16-QAM) are used, the nonlinear distortion caused by the use of HPAs is greatly minimized by our proposed NN predistorter and the performance of the communication system is significantly improved. / Thesis (Master, Electrical & Computer Engineering) -- Queen's University, 2007-08-08 14:55:50.489

This thesis investigated the abilities of artificial neural networks as rock classifiers in an open-pit hard rock environment using monitoring-while-drilling (MWD) data. Blast hole drilling data has been collected from an open-pit taconite mine. The data was smoothed with respect to depth and filtered for non-drilling data. Preliminary analysis was performed to determine classifier input variables and a method of labelling training data. Results obtained from principal component analysis suggested that the best set of possible classifier input variables was: penetration rate, torque, specific fracture energy, vertical vibration, horizontal vibration, penetration rate deviation and thrust deviation. Specific fracture energy and self-organizing-maps were explored as a means of labelling training data and found to be inadequate. Several backpropagation neural networks were trained and tested with various combinations of input parameters and training sets. Input sets that included all seven parameters achieved the best overall performances. 7-input neural networks that were trained with and tested on the entire data set achieved an average overall performance of 81%. A sensitivity analysis was performed to test the generalization abilities of the neural networks as rock classifiers. The best overall neural network performance on data not included in the training set was 67%. The results indicated that neural networks by themselves are not capable rock classifiers on MWD data in such a hard rock iron ore environment. / Thesis (Master, Mining Engineering) -- Queen's University, 2009-04-23 11:59:07.806

We explore the training of deep neural networks to produce vector representations using weakly labelled information in the form of binary similarity labels for pairs of training images. Previous methods such as siamese networks, IMAX and others, have used fixed cost functions such as $L_1$, $L_2$-norms and mutual information to drive the representations of similar images together and different images apart. In this work, we formulate learning as maximizing the likelihood of binary similarity labels for pairs of input images, under a parameterized probabilistic similarity model. We describe and evaluate several forms of the similarity model that account for false positives and false negatives differently. We extract representations of MNIST, AT\&T ORL and COIL-100 images and use them to obtain classification results. We compare these results with state-of-the-art techniques such as deep neural networks and convolutional neural networks. We also study our method from a dimensionality reduction prospective.