Goal of this thesis is to get familiar with problematics of neural networks and commonly used security protocols in cryptography. Theoretical part of the thesis is about neural networks theory and chooses best suitable type of neural network to use in cryptographic model. In practical part, a new type of security protocol is created, using chosen neural network.

This research investigates developing a training method for Restricted Hopfield Network (RHN) which is a subcategory of Hopfield Networks. Hopfield Networks are recurrent neural networks proposed in 1982 by John Hopfield. They are useful for different applications such as pattern restoration, pattern completion/generalization, and pattern association. In this study, we propose an enhanced training method for RHN which not only improves the convergence of the training sub-routine, but also is shown to enhance the learning capability of the network. Particularly, after describing the architecture/components of the model, we propose a modified variant of SPSA which in conjunction with back-propagation over time result in a training algorithm with an enhanced convergence for RHN. The trained network is also shown to achieve a better memory recall in the presence of noisy/distorted input. We perform several experiments, using various datasets, to verify the convergence of the training sub-routine, evaluate the impact of different parameters of the model, and compare the performance of the trained RHN in recreating distorted input patterns compared to conventional RBM and Hopfield network and other training methods.

No description available.

No description available.

The following work presents a new set of general methods for improving neural network accuracy on classification tasks, grouped under the label of classification-based methods. The central theme of these approaches is to provide problem representations and error functions that more directly improve classification accuracy than conventional learning and error functions. The CB1 algorithm attempts to maximize classification accuracy by selectively backpropagating error only on misclassified training patterns. CB2 incorporates a sliding error threshold to the CB1 algorithm, interpolating between the behavior of CB1 and standard error backpropagation as training progresses in order to avoid prematurely saturated network weights. CB3 learns a confidence threshold for each combination of training pattern and output class. This models an error function based on the performance of the network as it trains in order to avoid local overfit and premature weight saturation. PL1 is a point-wise local binning algorithm used to calibrate a learning model to output more accurate posterior probabilities. This algorithm is used to improve the reliability of classification-based networks while retaining their higher degree of classification accuracy. These approaches are demonstrated to be robust to a variety of learning parameter settings and have better classification accuracy than standard approaches on a variety of applications, such as OCR and speech recognition.

Predicting the next location of a user has been interesting for both academia and industry. Applications like location-based advertising, traffic planning, intelligent resource allocation as well as in recommendation services are some of the problems that many are interested in solving. Along with the technological advancement and the widespread usage of electronic devices, many location-based records are created. Today, deep learning framework has successfully surpassed many conventional methods in many learning tasks, most known in the areas of image and voice recognition. One of the neural network architecture that has shown the promising result at sequential data is Recurrent Neural Network (RNN). Since the creation of RNN, much alternative architecture have been proposed, and architectures like Long Short Term Memory (LSTM) and Gated Recurrent Units (GRU) are one of the popular ones that are created[5]. This thesis uses GRU architecture and features that incorporate time and location into the network to forecast people’s next location In this paper, a spatial-temporal neural network (ST-GRU) has been proposed. It can be seen as two parts, which are ST and GRU. The first part is a feature extraction algorithm that pulls out the information from a trajectory into location sequences. That process transforms the trajectory into a friendly sequence format in order to feed into the model. The second part, GRU is proposed to predict the next location given a user’s trajectory. The study shows that the proposed model ST-GRU has the best results comparing the baseline models. / Att förutspå vart en individ är på väg har varit intressant för både akademin och industrin. Tillämpningar såsom platsbaserad annonsering, trafikplanering, intelligent resursallokering samt rekommendationstjänster är några av de problem som många är intresserade av att lösa. Tillsammans med den tekniska utvecklingen och den omfattande användningen av elektroniska enheter har många platsbaserade data skapats. Idag har tekniken djupinlärning framgångsrikt överträffat många konventionella metoder i inlärningsuppgifter, bland annat inom områdena bild och röstigenkänning. En neural nätverksarkitektur som har visat lovande resultat med sekventiella data kallas återkommande neurala nätverk (RNN). Sedan skapandet av RNN har många alternativa arkitekturer skapats, bland de mest kända är Long Short Term Memory (LSTM) och Gated Recurrent Units (GRU). Den här studien använder en modifierad GRU där man bland annat lägger till attribut såsom tid och distans i nätverket för att prognostisera nästa plats. I det här examensarbetet har ett rumsligt temporalt neuralt nätverk (ST-GRU) föreslagits. Den består av två delar, nämligen ST och GRU. Den första delen är en extraktionsalgoritm som drar ut relevanta korrelationer mellan tid och plats som är inkorporerade i nätverket. Den andra delen, GRU, förutspår nästa plats med avseende på användarens aktuella plats. Studien visar att den föreslagna modellen ST-GRU ger bättre resultat jämfört med benchmarkmodellerna.

京都大学 / 新制・課程博士 / 博士(情報学) / 甲第24937号 / 情博第848号 / 新制||情||142(附属図書館) / 京都大学大学院情報学研究科先端数理科学専攻 / (主査)教授 林 和則, 教授 青柳 富誌生, 准教授 寺前 順之介 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

Fiber-optic systems represent the backbone of the communication networks, carrying most of the world’s data traffic. The main bottleneck in today’s fiber-optic communication systems has roots in the inherent nonlinearity of the fiber. Hence, developing new transmission schemes that are compatible with the nonlinear behavior of the optical fiber has become necessary. To utilize the full transmission capacity of an optical fiber, this thesis investigates two different techniques---compensation-based method and nonlinear Fourier transform (NFT). For the purpose of suppressing the nonlinear distortion in real time, an optical back propagation (OBP) technique using Raman pumped dispersion compensating fibers (DCF). OBP, as an all-optical signal processing technique, can compensate for both intra- and inter-channel nonlinear impairments in real time in point-to-point systems as well as in optical networks. The proposed inline OBP module consists of an optical phase conjugator (OPC), amplifiers and a Raman pumped DCF. In order to suppress the nonlinear effects of the transmission fiber, the power in the OBP fiber should increase exponentially with distance. This can be approximately achieved by using Raman pumping of the backpropagation fiber. Simulation results show that this technique provides 7.7 dB performance improvement in Q-factor over conventional systems. The second part of this thesis is dedicated to the NFT as a promising framework to exploit the inherent nonlinearity of optical fiber rather than treating it as an undesirable effect and using perturbation and approximation-based methods to mitigate it. A novel multistage perturbation technique to realize the NFT as a cascade of linear discrete Fourier transforms is developed. The linear Fourier transform can be easily implemented in the optical domain using a time lens or discrete photonic components, which can be implemented in silicon photonics. The proposed technique provides a promising way to implement NFT in the optical domain, which will fully utilize the potential of NFT for wavelength-division multiplexed fiber-optic systems in the optical domain. Moreover, a nonlinear frequency-division multiplexed (NFDM) transmission scheme with midpoint OPC is investigated. The proposed mid-OPC NFDM system offers a degree of freedom to have a flexible power normalization factor, P_n to minimize the signal-noise mixing in NFT processing for a specific launch power, resulting in significant system performance improvement up to 5.6 dB in Q-factor over conventional NFDM systems. Another advantage of the proposed scheme is that the mid-OPC NFDM system extends the transmission reach without having to increase the guard interval, which leads to higher spectral efficiency. / Thesis / Doctor of Philosophy (PhD)

Thesis (M.Sc.)--Universiteit van Suid-Afrika, 2002.

Traditional Inductive Logic Programming (ILP) focuses on the setting where the target theory is a generalisation of the observations. This is known as Observational Predicate Learning (OPL). In the Theory Completion setting the target theory is not in the same predicate as the observations (non-OPL). This thesis investigates two alternative simple extensions to traditional ILP to perform non-OPL or Theory Completion. Both techniques perform extraction-case abduction from an existing background theory and one seed observation. The first technique -- Logical Back-propagation -- modifies the existing background theory so that abductions can be achieved by a form of constructive negation using a standard SLD-resolution theorem prover. The second technique -- SOLD-resolution -- modifies the theorem prover, and leaves the existing background theory unchanged. It is shown that all abductions produced by Logical Back-propagation can also be generated by SOLD-resolution; but the reverse does not hold. The implementation using the SOLD-resolution technique -- the ALECTO system -- was applied to the problems of completing context free and context dependant grammars; and learning Event Calculus programs. It was successfully able to learn an Event Calculus program to control the navigation of a real-life robot. The Event Calculus is a formalism to represent common-sense knowledge. It follows that the discovery of some common-sense knowledge was produced with the assistance of a machine.