Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 39 for “"Neural Nets"”.
-
Using Deep Neural Nets in Writer Identification & Analysis
<p>This thesis focuses on developing automated deep learning methods for writer identification and writer attribute prediction from handwriting. It introduces two novel architectures: Convolutional Transformer Encoder (CTE) and Convolutional Swin Encoder (CSE). CTE is designed for determining …
-
Long-memory stochastic volatility model calibration using deep neural nets
… vanilla option. However, with the advent of neural networks, stochastic volatility models are becoming increasing tractable. The use of neural networks to learn the expectation function of the underlying stochastic volatility processes for calibration makes application of these more involved …
-
Time and accuracy tradeoff using artificial neural nets and genetic algorithms
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Mechanical Engineering, 2000.
-
Credit scoring models for Egyptian banks : neural nets and genetic programming versus conventional techniques
… Both advanced scoring techniques, namely, neural nets (probabilistic neural nets and multi-layer feed-forward nets) and genetic programming, and conventional techniques, namely, a weight of evidence measure, multiple discriminant analysis, probit analysis and logistic regression were used …
-
Improving Bio-Inspired Frameworks
… bio-inspired algorithm we address is for Deep Neural Networks. With the increasing prevalence of Neural Nets in artificial intelligence and mission-critical applications such as self-driving cars, questions arise about its reliability and robustness. We have developed a test-generation based …
-
Developing neural network applications using LabVIEW
Artificial Neural Networks (ANN) have gained tremendous popularity over the last few decades. They are considered as substitutes for classical techniques which have been followed for many years. Many neural network architectures and training algorithms have been developed so far. Different aspects …
-
Improved Friction and Dynamics Estimation in Legged Robots
… the effect of using single-layer feed-forward neural nets to model non-linear friction forces and other forms of dynamics that are difficult to account for with traditional robot system identification schemes. Applying the single-layer feed-forward neural nets to system identification data from …
-
A search for supersymmetry with the ATLAS detector, and the use of machine learning techniques for object classification in high energy physics
… searches in the future, including the use of neural nets on calorimeter data for particle-type classification, particle energy regression, and shower generation.
-
A comparative study of different methods of predicting time series
… second approach is using the concept of training neural nets and pattern recognition. This involves in designing a neural network and training it using different learning methods. The learning algorithms used in the current work involves the backpropagation method, recurrent nets learning method, …
-
Automatic Control Strategies of Mean Arterial Pressure and Cardiac Output. MIMO controllers, PID, internal model control, adaptive model reference, and neural nets are developed to regulate mean arterial pressure and cardiac output using the drugs sodium Nitroprusside and dopamine
… to that shortcoming, a PID controller using a Neural Network that tunes the controller parameters was designed and implemented. The parameters of the PID controller were optimised offline using Matlab genetic algorithm. The proposed Neuro-PID controller has been tested and validated to …
-
Approximation of CPU code using neural networks
… function compared to an equivalent CPU function. Neural nets are fairly general purpose tools which can perform pattern recognition or arithmetic operations on a block of input data and produce a corresponding block of output data. The aim of this project is to be able to select a fairly arbitrary …
-
Modeling user network transitions : various approaches
… including probabilistic programming, regression, neural nets, and clustering algorithms. We compare and contrast how models differ in their prediction accuracy, speed of convergence, and algorithmic complexity.
-
Applied Plankton Image Classification for Imaging FlowCytobot Data
… of plankton gathered by the IFCB - Convolutional Neural Nets (CNNs), Vision Transformers (ViT), and self-supervised learning (MAE). The benefits and downsides of each model are analyzed and discussed for future IFCB operators to process their data using the methods that best align with their …
-
Computational perception of physical object properties
… or a mature physics engine, with deep neural nets. Our extensive evaluations demonstrate that these models can learn physical object properties well and, with a physic engine, the responses of the model positively correlate with human responses. Future research directions include …
-
Initial analysis towards a measurement of the branching fractions B [right arrow] [rho][gamma] and B [right arrow] [omega][gamma]
… from the high levels of continuum background. Neural nets that can consider correlations between variables have also been implemented to suppress the continuum. Preliminary results using Monte Carlo are discussed. Final values using runs 1 through 5 of the BaBar experimental data will be …
-
Novel angular and frequency manipulation of light in nano-scaled dielectric photonic systems
… We first mathematically prove that conventional neural networks architecture can be equivalently represented by nanoscaled optical systems. We then experimentally demonstrate that our optical neural networks are able to give equivalent accuracy on a standard training datasets. In the last part, …
-
Turing machines, computers and artificial intelligence
… machines. Analog computers and real or simulated neural nets exhibit properties that may not be accommodated in a definition of computing, which is based on Turing machines. Consequently, some of the philosophical 'in principle' objections to artificial intelligence may not apply in reference to …
-
Dynamic grid adaption using the LPE equation
… to adapt grids to solution phenomena using neural nets is demonstrated.
-
High-order tuners for convex optimization : stability and accelerated learning
… of machine learning models including large neural-nets. In particular, momentum-based methods, with accelerated learning guarantees, have received a lot of attention due to their provable guarantees of fast learning in certain classes of problems and multiple algorithms have been derived. …
-
Universal approximation of input-output maps and dynamical systems by neural network architectures
It is well known that feedforward neural networks can approximate any continuous function supported on a finite-dimensional compact set to arbitrary accuracy. However, many engineering applications require modeling infinite-dimensional functions, such as sequence-to-sequence transformations or …
Page 1 of 2