A ideia de usar redes neurais biologicamente inspiradas na computação tem sido amplamente utilizada nas últimas décadas. O fato essencial neste paradigma é que um neurônio pode integrar e processar informações, e esta informação pode ser revelada por sua atividade de pulsos. Ao descrever a dinâmica de um único neurônio usando um modelo matemático, uma rede pode ser implementada utilizando um conjunto desses neurônios, onde a atividade pulsante de cada neurônio irá conter contribuições, ou informações, da atividade pulsante da rede em que está inserido. Neste trabalho é apresentado um controlador de posição no eixo Z utilizando fusão de sensores baseado no paradigma de Redes Neurais Recorrentes. O sistema proposto utiliza uma Máquina de Estado Líquido (LSM) para controlar o robô colaborativo BAXTER. O framework foi projetado para trabalhar em paralelo com as LSMs que executam trajetórias em formas fechadas de duas dimensões, com o objetivo de manter uma caneta de feltro em contato com a superfície de desenho, dados de sensores de força e distância são alimentados ao controlador. O sistema foi treinado utilizando dados de um controlador Proporcional Integral Derivativo (PID), fundindo dados de ambos sensores. Resultados mostram que a LSM foi capaz de aprender o comportamento do controlador PID em diferentes situações. / The idea of employing biologically inspired neural networks to perform computation has been widely used over the last decades. The essential fact in this paradigm is that a neuron can integrate and process information, and this information can be revealed by its spiking activity. By describing the dynamics of a single neuron using a mathematical model, a network in which the spiking activity of every single neuron will get contributions, or information, from the spiking activity of the embedded network. A positioning controller based on Spiking Neural Networks for sensor fusion suitable to run on a neuromorphic computer is presented in this work. The proposed framework uses the paradigm of reservoir computing to control the collaborative robot BAXTER. The system was designed to work in parallel with Liquid State Machines that performs trajectories in 2D closed shapes. In order to keep a felt pen touching a drawing surface, data from sensors of force and distance are fed to the controller. The system was trained using data from a Proportional Integral Derivative controller, merging the data from both sensors. The results show that the LSM can learn the behavior of a PID controller on di erent situations.

A ideia de usar redes neurais biologicamente inspiradas na computação tem sido amplamente utilizada nas últimas décadas. O fato essencial neste paradigma é que um neurônio pode integrar e processar informações, e esta informação pode ser revelada por sua atividade de pulsos. Ao descrever a dinâmica de um único neurônio usando um modelo matemático, uma rede pode ser implementada utilizando um conjunto desses neurônios, onde a atividade pulsante de cada neurônio irá conter contribuições, ou informações, da atividade pulsante da rede em que está inserido. Neste trabalho é apresentado um controlador de posição no eixo Z utilizando fusão de sensores baseado no paradigma de Redes Neurais Recorrentes. O sistema proposto utiliza uma Máquina de Estado Líquido (LSM) para controlar o robô colaborativo BAXTER. O framework foi projetado para trabalhar em paralelo com as LSMs que executam trajetórias em formas fechadas de duas dimensões, com o objetivo de manter uma caneta de feltro em contato com a superfície de desenho, dados de sensores de força e distância são alimentados ao controlador. O sistema foi treinado utilizando dados de um controlador Proporcional Integral Derivativo (PID), fundindo dados de ambos sensores. Resultados mostram que a LSM foi capaz de aprender o comportamento do controlador PID em diferentes situações. / The idea of employing biologically inspired neural networks to perform computation has been widely used over the last decades. The essential fact in this paradigm is that a neuron can integrate and process information, and this information can be revealed by its spiking activity. By describing the dynamics of a single neuron using a mathematical model, a network in which the spiking activity of every single neuron will get contributions, or information, from the spiking activity of the embedded network. A positioning controller based on Spiking Neural Networks for sensor fusion suitable to run on a neuromorphic computer is presented in this work. The proposed framework uses the paradigm of reservoir computing to control the collaborative robot BAXTER. The system was designed to work in parallel with Liquid State Machines that performs trajectories in 2D closed shapes. In order to keep a felt pen touching a drawing surface, data from sensors of force and distance are fed to the controller. The system was trained using data from a Proportional Integral Derivative controller, merging the data from both sensors. The results show that the LSM can learn the behavior of a PID controller on di erent situations.

The first part of this dissertation (Chapters 1 to 4) describes the use of magnetic resonance techniques for polymeric material characterizations in solutions, with emphasis on methods utilizing magnetic field gradients - magnetic resonance imaging (MRI) and pulsed-field-gradient (PFG) NMR. The second part (Chapter 5) presents enhancements to dynamic nuclear polarization, an intensity enhancement approach for magnetic resonance techniques. In Chapter 2, I illustrate a characterization method to quantify free polymer chain content in a polymer/DNA complex (polyplex) formulation via one-dimensional proton NMR experiments. This assessment of free polymer quantity has critical impacts on in vivo gene transfection efficiency, cellular uptake, as well as toxicity of polycationic gene delivery vectors. Specifically, I investigated the complexation properties of three different polymeric "theranostic" agents, which combine an imaging functionality on the polymer as well as a DNA/RNA complexation component. These agents are under development to allow real time clinical monitoring of drug delivery and efficacy using MRI. Our NMR method provides simple and quantitative assessment of free and DNA-complexed polymers, including the actual polymer amine to DNA phosphate molar ratio (N/P ratio) within polyplexes. The NMR results are in close agreement with the stoichiometric number of polymer/DNA binding obtained by isothermal titration calorimetry. The noninvasive nature of this method allows broad application to a range of polyelectrolyte coacervates, for understanding and optimizing polyelectrolyte complex formation. Chapter 3 demonstrates a time-resolved MRI approach for measuring diffusion of drug-delivery polymeric nanoparticles on mm to cm scales as well as monitoring nanoparticle concentration distribution in bulk biological hydrogels. Our results show that as the particle size and surface charge become larger, collagen gel at tumor relevant concentration (1.0 wt.%) presents a more significant impediment to the diffusive transport of negatively charged nanoparticles. These results agree well with those obtained by fluorescence spectroscopies (neutral or slightly positively charged diffusing particles) as well as the proposed electrostatic bandpass theory of tumor interstitium (negatively charged particles). This study provides fundamental information for the design of polymeric theranostic vectors and carries implications that would benefit the understanding of nanoparticle transport in solid tumors. Furthermore, this work takes a significant step toward developing quantitative and real time in vivo monitoring of clinical drug delivery using MRI. Chapter 4 addresses the application of PFG-NMR for the determination of weight-average molar mass (Mw) for polyanions that have anti-HIV activity through the measurement of polymer diffusion coefficients in solutions. The effective characterization of molecular weights of polyelectrolytes has been a general and growing problem for the polymer industry, with no clear solutions in sight. In this study, we obtained the molar masses (Mw) for two series of sulfonated copolymers using sodium polystyrene sulfonate samples as molecular weight standards. PFG-NMR has notable advantages over conventional techniques for the characterization of charged polymers and shows great promise for becoming an effective alternative to chromatography methods. Chapter 5 is devoted to experimental and theoretical studies of liquid state dynamic nuclear polarization (DNP) via the Overhauser effect. Based on the adventurous work done by previous Dorn group members, we show that for 1H-nuclide-containing systems, the dipolar DNP enhancement can be significantly improved by decreasing the correlation time of the interaction by utilizing a supercritical fluid (SF CO2) which allows for greater dipolar enhancements at higher magnetic fields. For molecules containing the ubiquitous 13C nuclide, we show that previously unreported sp hybridized (H-C) alkyne systems represented by the phenylacetylene-nitroxide system exhibit very large scalar-dominated enhancements. Furthermore, we show for a wide range of molecular systems that the Fermi contact interaction can be computationally predicted via electron-nuclear hyperfine coupling and correlated with experimental 13C DNP enhancements. For biomedical applications, the enhancement of metabolites in SF CO2 followed by rapid dissolution in water or biological fluids is an attractive approach for future hyperpolarized NMR and MRI applications. Moreover, with the aid of density functional theory calculations, solution state DNP provides a unique approach for studying intermolecular weak bonding interaction of solutes in normal liquids and SF fluids. / Ph. D.

In this thesis, theoretical and computer simulation studies of vibrational phase relaxation in various molecular liquids are presented. That includes liquid nitrogen, both along the coexistence line and the critical isochore, binary liquid mixture and liquid water. The focus of the thesis is to understand the dependence of the vibrational relaxation on the density, temperature, composition and the role of different interactions among the molecules. The density fluctuation of the solute particles in a solvent is studied systematically, where the computer simulation results are compared with the mode coupling theory (MCT). The classical density functional theory (DFT) is used to study the vibrational relaxation dynamics in molecular liquids with an aim to understand the heterogeneous nature of the dynamics commonly observed in experiments. Chapter 1 contains a brief overview of the earlier relevant theories, their successes and shortcomings in the light of the problems discussed in this thesis. This chapter discusses mainly the basic features of the vibrational dynamics of molecular liquids and portrays some of the theoretical frameworks and formalisms which are widely recognized to have contributed to our present understanding. Vibrational dephasing of nitrogen molecules is known to show highly interesting anomalies near its gas–liquid critical point. In Chapter 2, we present the results of extensive computer simulation studies and theoretical analysis of the vibrational phase relaxation of nitrogen molecules both along the critical isochore and the gas–liquid coexistence line. The simulation includes the different contributions (density (ρ), vibration–rotation (VR), and resonant transfer (Rs)) and their cross–correlations. Following Everitt and Skinner, we have included the vibrational coordinate (q) dependence of the inter–atomic potential, which is found to have an important contribution. The simulated results are in good agreement with the experiments. The linewidth (directly proportional to the rate of the vibrational phase relaxation) is found to have a lambda shaped temperature dependence near the critical point. As observed in the experimental studies, the calculated lineshape becomes Gaussian–like as the critical temperature (Tc) is approached while being Lorentzian–like at the temperatures away from Tc. Both the present simulation and a mode coupling theory (MCT) analysis show that the slow decay of the enhanced density fluctuations near the critical point (CP), probed at the sub–picosecond timescales by the vibrational frequency modulation, and an enhanced vibration–rotation coupling, are the main causes of the observed anomalies. Dephasing time (тv) and the root mean square frequency fluctuation (Δ) in the supercritical region are calculated. The principal results are: 1. a crossover from a Lorentzian–like to a Gaussian–like lineshape is observed as the critical point is approached along the critical isochore, 2. the root mean square frequency fluctuation shows a non–monotonic dependence on the temperature along the critical isochore, 3. the temperature dependent linewidth shows a divergence–like (λ–shaped) behavior along the coexistence line and the critical isochore. It is found that the linewidth calculated from the time integral of the normal coordinate time correlation function (CQ(t)) is in good agreement with the known experimental results. The origin of the anomalous temperature dependence of linewidth can be traced to simultaneous effects of several factors, (i) the enhancement of the negative cross–correlations of ρ with VR and Rs and (ii) the large density fluctuations as the critical point (CP) is approached. Due to the negative cross–correlations of ρ with VR and Rs the total decay becomes faster (correlation times are in the femtosecond scale). The reason for the negative cross–correlation between ρ and VR is explored in detail. A mode coupling theory (MCT) analysis shows a slow decay of the enhanced density fluctuations near the critical point. The MCT analysis demonstrates that the large enhancement of VR–coupling near CP may arise from a non–Gaussian behavior of the equilibrium density fluctuations. This enters through a non–zero value of the triplet direct correlation function. Many of the complex systems found in nature and used routinely in industry are multi–component systems. In particular, binary mixtures are highly non–ideal and play an important role in the industry. The dynamic properties are strongly influenced by composition fluctuations which are absent in the one component liquids. In Chapter 3, isothermal–isobaric (NPT) ensemble molecular dynamics simulation studies of vibrational phase relaxation (VPR) in a model system are presented. The model considers strong attractive interaction between the dissimilar species to prevent phase separation. The model reproduces the experimentally observed non–monotonic, nearly symmetric, composition dependence of the dephasing rate. In addition, several other experimentally observed features, such as the maximum of the frequency modulation correlation time (т c) at a mole fraction near 0.5 and the maximum rate enhancement by a factor of about 3 above the pure component value, are also reproduced. The product of the mean square frequency modulation ((Δω2(0))) with тc indicates that the present model is in the intermediate regime of the inhomogeneous broadening. The non–monotonic composition (χ) dependence of тv is found to be primarily due to the non–monotonic χ dependence of тc, rather than due to a similar dependence in the amplitude of (Δω2(0)). The probability distribution of Δω shows a markedly non–Gaussian behavior at intermediate composition (χ - 0.5). We have also calculated the composition dependence of the viscosity (η∗) in order to explore the correlation between the viscosity with that of тv and тc. It is found that both the correlation times essentially follow the nature of the composition dependence of the viscosity. A mode coupling theory (MCT) analysis is presented to include the effects of the composition fluctuations in binary mixture. Water is an interesting and attractive object for research, not only because of its great importance in life processes but also due to its unusual and intriguing properties. Most of the anomalous properties of water are related to the presence of a three–dimensional network of hydrogen bonds, which is constantly changing at ultrafast, sub–picosecond timescales. Vibrational spectroscopy provides the means to study the dynamics of processes involving only certain chemical bonds. The dynamics of hydrogen bonding can be probed via its reflection on molecular vibrations, e.g., the stretching vibrational mode of the O–H bond. Recently developed femtosecond infrared vibrational spectroscopy has proved to be valuable to study water dynamics because of its unique temporal resolution. Recent studies have shown that the vibrational relaxation of the O–H stretch of HDO occurs at an extremely fast timescale with time constant being less than 100 femtosecond. Here, in Chapter 4, we investigate the origin of this ultrafast vibrational dephasing using computer simulation and appropriate theoretical analysis. In addition to the usual fast vibrational dynamics due to the hydrogen bonding excitations, we find two additional reasons: (a) the large amplitude of angular jumps of the water molecules (with 30–40 fs time intervals) provide large contribution to the mean square vibrational frequency and (b) the projected force along the O–H bond due to the solvent molecules, on the oxygen (FO(t)) and hydrogen (FH (t)) atoms of the O–H bond exhibit a large negative cross–correlation (NCC) between FO(t) and FH (t). This NCC is shown to be partly responsible for a weak, non–Arrhenius temperature dependence of the relaxation rate. In the concluding note, Chapter 5 starts with a brief summary of the outcome of this thesis and ends up with suggestions of a few relevant problems that may prove worthwhile to be addressed in the future.

No description available.

Les liquides diffèrent des solides par une réponse retardée à la sollicitation en cisaillement; c’est-à-dire une absence d’élasticité de cisaillement et un comportement d'écoulement à basses fréquences (<1 Hz). Ce postulat pourrait ne pas être vrai à toutes échelles. A l’échelle submillimétrique, les mesures viscoélastiques (VE) réalisées en améliorant l'interaction entre le liquide et le substrat, montrent qu’une élasticité basses-fréquences existe dans des liquides aussi variés que les polymères, les surfondus, les liquides à liaison H, ioniques ou van der Waals. Ce résultat implique que les molécules à l'état liquide ne seraient pas dynamiquement libres, mais élastiquement corrélées.En utilisant les propriétés biréfringentes des fluctuations prétransitionnelles qui coexistent dans la phase isotrope des cristaux liquides, nous montrons qu'il est possible de visualiser ces corrélations « cachées ». Dans des conditionssimilaires aux mesures VE, une biréfringence optique synchrone à la déformation est observée dans la phase isotrope à des fréquences aussi basses que 0.01 Hz et des températures éloignées de toute transition. Le comportement dela biréfringence basses-fréquences a des similitudes avec l'élasticité; elle est en phase avec la déformation à faibles amplitudes de déformation, puis en phase avec le taux de déformation à plus grandes amplitudes. La biréfringence basses- fréquences est forte, sans défaut et réversible. Elle indique un ordre à longue portée. La synchronisation de la réponse à la sollicitation en fréquence et l’état ordonné qu’elle produit ne sont pas compatibles avec un état liquide isotrope mais montrent qu’il s’agit d’un état élastique soumis à déformation (entropie élastique). / Liquids differ from solids by a delayed response to a shear mechanical solicitation; i.e. they have no shearelasticity and exhibit a flow behaviour at low frequency (<1 Hz). This postulate might be not verified at thesub-millimeter scale. By optimizing the measurement in particular by improving the liquid/substrate interactions (wetting), a low frequency shear elasticity has been found in liquids including molten polymers, glass-formers, H-bond polar, ionic or van der Waals liquids. This result implies that molecules in the liquid state may not be dynamically free but weaklyelastically correlated. Using the birefringent properties of the pretransitional fluctuations coexisting in the isotropic phase of liquid crystals, we show that it is possible to visualize these “hidden” shear-elastic correlations. We detect a synchronized birefringent optical response in the isotropic phase that is observable at frequencies as low as 0.01 Hz and at temperatures far away from anyphase transition. The low-frequency birefringence exhibits a strain dependence similar to the low frequency elasticity: An optical signal that is in-phase with the strain at low strain amplitudes and in-phase with the strain-rate at larger strain amplitudes. The birefringent response is strong, defect-free, reversible and points out a collective response. This long-range ordering rules out the condition of an isotropic liquid and its synchronized response supports the existenceof long-range elastic (solid-like) correlations. In the light of this, the strain dependence of the harmonic birefringent signal and the shear elasticity may correspond to an entropy-driven transition.

<p>Deep ‘Analog Artificial Neural Networks’ (AANNs) perform complex classification problems with high accuracy. However, they rely on humongous amount of power to perform the calculations, veiling the accuracy benefits. The biological brain on the other hand is significantly more powerful than such networks and consumes orders of magnitude less power, indicating some conceptual mismatch. Given that the biological neurons are locally connected, communicate using energy efficient trains of spikes, and the behavior is non-deterministic, incorporating these effects in Artificial Neural Networks (ANNs) may drive us few steps towards a more realistic neural networks. </p> <p> </p> <p>Emerging devices can offer a plethora of benefits including power efficiency, faster operation, low area in a vast array of applications. For example, memristors and Magnetic Tunnel Junctions (MTJs) are suitable for high density, non-volatile Random Access Memories when compared with CMOS implementations. In this work, we analyze the possibility of harnessing the characteristics of such emerging devices, to achieve neuro-inspired solutions to intricate problems.</p> <p> </p> <p>We propose how the inherent stochasticity of nano-scale resistive devices can be utilized to realize the functionality of spiking neurons and synapses that can be incorporated in deep stochastic Spiking Neural Networks (SNN) for image classification problems. While ANNs mainly dwell in the aforementioned classification problem solving domain, they can be adapted for a variety of other applications. One such neuro-inspired solution is the Cellular Neural Network (CNN) based Boolean satisfiability solver. Boolean satisfiability (k-SAT) is an NP-complete (k≥3) problem that constitute one of the hardest classes of constraint satisfaction problems. We provide a proof of concept hardware based analog k-SAT solver that is built using MTJs. The inherent physics of MTJs, enhanced by device level modifications, is harnessed here to emulate the intricate dynamics of an analog, CNN based, satisfiability (SAT) solver. </p> <p> </p> <p>Furthermore, in the effort of reaching human level performance in terms of accuracy, increasing the complexity and size of ANNs is crucial. Efficient algorithms for evaluating neural network performance is of significant importance to improve the scalability of networks, in addition to designing hardware accelerators. We propose a scalable approach for evaluating Liquid State Machines: a bio-inspired computing model where the inputs are sparsely connected to a randomly interlinked reservoir (or liquid). It has been shown that biological neurons are more likely to be connected to other neurons in the close proximity, and tend to be disconnected as the neurons are spatially far apart. Inspired by this, we propose a group of locally connected neuron reservoirs, or an ensemble of liquids approach, for LSMs. We analyze how the segmentation of a single large liquid to create an ensemble of multiple smaller liquids affects the latency and accuracy of an LSM. In our analysis, we quantify the ability of the proposed ensemble approach to provide an improved representation of the input using the Separation Property (SP) and Approximation Property (AP). Our results illustrate that the ensemble approach enhances class discrimination (quantified as the ratio between the SP and AP), leading to improved accuracy in speech and image recognition tasks, when compared to a single large liquid. Furthermore, we obtain performance benefits in terms of improved inference time and reduced memory requirements, due to lower number of connections and the freedom to parallelize the liquid evaluation process.</p>

Establishing and maintaining successful communication stands as a critical prerequisite for achieving the goals of inducing and studying advanced computation in small-scale living neuronal networks. The following work establishes a novel and effective method for communicating arbitrary "sensory" input information to cultures of living neurons, living neuronal networks (LNNs), consisting of approximately 20 000 rat cortical neurons plated on microelectrode arrays (MEAs) containing 60 electrodes. The sensory coding algorithm determines a set of effective codes (symbols), comprised of different spatio-temporal patterns of electrical stimulation, to which the LNN consistently produces unique responses to each individual symbol. The algorithm evaluates random sequences of candidate electrical stimulation patterns for evoked-response separability and reliability via a support vector machine (SVM)-based method, and employing the separability results as a fitness metric, a genetic algorithm subsequently constructs subsets of highly separable symbols (input patterns). Sustainable input/output (I/O) bit rates of 16-20 bits per second with a 10% symbol error rate resulted for time periods of approximately ten minutes to over ten hours. To further evaluate the resulting code sets' performance, I used the system to encode approximately ten hours of sinusoidal input into stimulation patterns that the algorithm selected and was able to recover the original signal with a normalized root-mean-square error of 20-30% using only the recorded LNN responses and trained SVM classifiers. Response variations over the course of several hours observed in the results of the sine wave I/O experiment suggest that the LNNs may retain some short-term memory of the previous input sample and undergo neuroplastic changes in the context of repeated stimulation with sensory coding patterns identified by the algorithm.

Site characterization is an important task in Geotechnical Engineering. In situ tests based on standard penetration test (SPT), cone penetration test (CPT) and shear wave velocity survey are popular among geotechnical engineers. Site characterization using any of these properties based on finite number of in-situ test data is an imperative task in probabilistic site characterization. These methods have been used to design future soil sampling programs for the site and to specify the soil stratification. It is never possible to know the geotechnical properties at every location beneath an actual site because, in order to do so, one would need to sample and/or test the entire subsurface profile. Therefore, the main objective of site characterization models is to predict the subsurface soil properties with minimum in-situ test data. The prediction of soil property is a difficult task due to the uncertainities. Spatial variability, measurement ‘noise’, measurement and model bias, and statistical error due to limited measurements are the sources of uncertainities. Liquefaction in soil is one of the other major problems in geotechnical earthquake engineering. It is defined as the transformation of a granular material from a solid to a liquefied state as a consequence of increased pore-water pressure and reduced effective stress. The generation of excess pore pressure under undrained loading conditions is a hallmark of all liquefaction phenomena. This phenomena was brought to the attention of engineers more so after Niigata(1964) and Alaska(1964) earthquakes. Liquefaction will cause building settlement or tipping, sand boils, ground cracks, landslides, dam instability, highway embankment failures, or other hazards. Such damages are generally of great concern to public safety and are of economic significance. Site-spefific evaluation of liquefaction susceptibility of sandy and silty soils is a first step in liquefaction hazard assessment. Many methods (intelligent models and simple methods as suggested by Seed and Idriss, 1971) have been suggested to evaluate liquefaction susceptibility based on the large data from the sites where soil has been liquefied / not liquefied. The rapid advance in information processing systems in recent decades directed engineering research towards the development of intelligent models that can model natural phenomena automatically. In intelligent model, a process of training is used to build up a model of the particular system, from which it is hoped to deduce responses of the system for situations that have yet to be observed. Intelligent models learn the input output relationship from the data itself. The quantity and quality of the data govern the performance of intelligent model. The objective of this study is to develop intelligent models [geostatistic, artificial neural network(ANN) and support vector machine(SVM)] to estimate corrected standard penetration test (SPT) value, Nc, in the three dimensional (3D) subsurface of Bangalore. The database consists of 766 boreholes spread over a 220 sq km area, with several SPT N values (uncorrected blow counts) in each of them. There are total 3015 N values in the 3D subsurface of Bangalore. To get the corrected blow counts, Nc, various corrections such as for overburden stress, size of borehole, type of sampler, hammer energy and length of connecting rod have been applied on the raw N values. Using a large database of Nc values in the 3D subsurface of Bangalore, three geostatistical models (simple kriging, ordinary kriging and disjunctive kriging) have been developed. Simple and ordinary kriging produces linear estimator whereas, disjunctive kriging produces nonlinear estimator. The knowledge of the semivariogram of the Nc data is used in the kriging theory to estimate the values at points in the subsurface of Bangalore where field measurements are not available. The capability of disjunctive kriging to be a nonlinear estimator and an estimator of the conditional probability is explored. A cross validation (Q1 and Q2) analysis is also done for the developed simple, ordinary and disjunctive kriging model. The result indicates that the performance of the disjunctive kriging model is better than simple as well as ordinary kriging model. This study also describes two ANN modelling techniques applied to predict Nc data at any point in the 3D subsurface of Bangalore. The first technique uses four layered feed-forward backpropagation (BP) model to approximate the function, Nc=f(x, y, z) where x, y, z are the coordinates of the 3D subsurface of Bangalore. The second technique uses generalized regression neural network (GRNN) that is trained with suitable spread(s) to approximate the function, Nc=f(x, y, z). In this BP model, the transfer function used in first and second hidden layer is tansig and logsig respectively. The logsig transfer function is used in the output layer. The maximum epoch has been set to 30000. A Levenberg-Marquardt algorithm has been used for BP model. The performance of the models obtained using both techniques is assessed in terms of prediction accuracy. BP ANN model outperforms GRNN model and all kriging models. SVM model, which is firmly based on the theory of statistical learning theory, uses regression technique by introducing -insensitive loss function has been also adopted to predict Nc data at any point in 3D subsurface of Bangalore. The SVM implements the structural risk minimization principle (SRMP), which has been shown to be superior to the more traditional empirical risk minimization principle (ERMP) employed by many of the other modelling techniques. The present study also highlights the capability of SVM over the developed geostatistic models (simple kriging, ordinary kriging and disjunctive kriging) and ANN models. Further in this thesis, Liquefaction susceptibility is evaluated from SPT, CPT and Vs data using BP-ANN and SVM. Intelligent models (based on ANN and SVM) are developed for prediction of liquefaction susceptibility using SPT data from the 1999 Chi-Chi earthquake, Taiwan. Two models (MODEL I and MODEL II) are developed. The SPT data from the work of Hwang and Yang (2001) has been used for this purpose. In MODEL I, cyclic stress ratio (CSR) and corrected SPT values (N1)60 have been used for prediction of liquefaction susceptibility. In MODEL II, only peak ground acceleration (PGA) and (N1)60 have been used for prediction of liquefaction susceptibility. Further, the generalization capability of the MODEL II has been examined using different case histories available globally (global SPT data) from the work of Goh (1994). This study also examines the capabilities of ANN and SVM to predict the liquefaction susceptibility of soils from CPT data obtained from the 1999 Chi-Chi earthquake, Taiwan. For determination of liquefaction susceptibility, both ANN and SVM use the classification technique. The CPT data has been taken from the work of Ku et al.(2004). In MODEL I, cone tip resistance (qc) and CSR values have been used for prediction of liquefaction susceptibility (using both ANN and SVM). In MODEL II, only PGA and qc have been used for prediction of liquefaction susceptibility. Further, developed MODEL II has been also applied to different case histories available globally (global CPT data) from the work of Goh (1996). Intelligent models (ANN and SVM) have been also adopted for liquefaction susceptibility prediction based on shear wave velocity (Vs). The Vs data has been collected from the work of Andrus and Stokoe (1997). The same procedures (as in SPT and CPT) have been applied for Vs also. SVM outperforms ANN model for all three models based on SPT, CPT and Vs data. CPT method gives better result than SPT and Vs for both ANN and SVM models. For CPT and SPT, two input parameters {PGA and qc or (N1)60} are sufficient input parameters to determine the liquefaction susceptibility using SVM model. In this study, an attempt has also been made to evaluate geotechnical site characterization by carrying out in situ tests using different in situ techniques such as CPT, SPT and multi channel analysis of surface wave (MASW) techniques. For this purpose a typical site was selected wherein a man made homogeneous embankment and as well natural ground has been met. For this typical site, in situ tests (SPT, CPT and MASW) have been carried out in different ground conditions and the obtained test results are compared. Three CPT continuous test profiles, fifty-four SPT tests and nine MASW test profiles with depth have been carried out for the selected site covering both homogeneous embankment and natural ground. Relationships have been developed between Vs, (N1)60 and qc values for this specific site. From the limited test results, it was found that there is a good correlation between qc and Vs. Liquefaction susceptibility is evaluated using the in situ test data from (N1)60, qc and Vs using ANN and SVM models. It has been shown to compare well with “Idriss and Boulanger, 2004” approach based on SPT test data. SVM model has been also adopted to determine over consolidation ratio (OCR) based on piezocone data. Sensitivity analysis has been performed to investigate the relative importance of each of the input parameters. SVM model outperforms all the available methods for OCR prediction.