This thesis examines how convolutional neural networks can applied to the problem of hand detection and hand pose estimation. Two families of convolutional neural networks are trained, aimed at performing the task of classification or regression. The networks are trained on specialized data generated from publicly available datasets. The algorithms used to generate the specialized data are also disclosed. The main focus has been to investigate the different structural properties of convolutional neural networks, not building optimized hand detection, or hand pose estimation, systems. Experiments revealed, that classifier networks featuring a relatively high number of convolutions offers the highest performance on external validation data. Additionally, shallow classifier networks featuring a relatively low number of convolutions, yields a high classification accuracy on training and testing data, but a very low accuracy on the validation set. This effect uncovers one of the fundamental difficulties in building a hand detection system: The asymmetric classification problem. In further investigation, it is also remarked, that relatively shallow classifier networks probably becomes color sensitive. Furthermore, regressor networks featuring multiscale inputs typically yielded the lowest error, when tasked with computing key-point locations directly from data. It is also revealed, that color data implicitly contain more information, making it easier to compute key-point locations, especially in the image space. However, to be able to derive the color invariant features, deeper regressor networks are required. / I detta examensarbete undersöks hur faltande neuronnät kan användas för detektering av, samt skattning av pose hos, händer. Två familjer av neuronnät tränas, med syftet att utföra klassificering eller regression. Neuronnäten tränas med specialiserad data genererad ur publikt tillgängliga dataset. Algoritmerna för att generera den specialiserade datan presenteras även i sin helhet. Huvudsyftet med arbetet, har varit att undersöka neuronnätens strukturella egenskaper, samt relatera dessa till prestanda, och inte bygga ett färdigt system för handdetektering eller skattning av handpose. Experimenten visade, att neuronnät för klassificering med ett relativt stor antal faltningar ger högst prestanda på valideringsdata. Vidare, så verkar neuronnät för klassificering med relativt litet antal faltningar ge en god prestanda på träning- och testdata, men mycket dålig prestand på valideringsdata. Detta sambandet avslöjar en fundamental svårighet med att träna ett neuronnät för klassificering av händer, nämligen det kraftigt asymmetriska klassificeringsproblemet. I vidare undersökningar visar det sig också, att neuronnät för klassificering med ett relativt litet antal faltningar troligtvis enbart blir färgkänsliga. Experimenten visade också, att neuronnät för regression som använde sig av data i flera skalor gav lägst fel när de skulle beräkna positioner av handmarkörer direkt ur data. Slutligen framkom det, att färgdata, i konstrast till djupdata, implicit innehåller mer information, vilket gör det relativt sett lättare att beräkna markörer, framför allt i det tvådimensionella bildrummet. Dock, för att kunna få fram den implicita informationen, så krävs relativt djupa neuronnät.

With the rise of social media and publicly available data, opinion mining is more accessible than ever. It is valuable for content creators, companies and advertisers to gain insights into what users think and feel. This work examines comments on YouTube videos, and builds a deep learning classifier to automatically determine their sentiment. Four Long Short-Term Memory-based models are trained and evaluated. Experiments are performed to determine which deep learning model performs with the best accuracy, recall, precision, F1 score and ROC curve on a labelled YouTube Comment dataset. The results indicate that a BiLSTM-based model has the overall best performance, with the accuracy of 89%. Furthermore, the four LSTM-based models are evaluated on an IMDB movie review dataset, achieving an average accuracy of 87%, showing that the models can predict the sentiment of different textual data. Finally, a statistical analysis is performed on the YouTube videos, revealing that videos with positive sentiment have a statistically higher number of upvotes and views. However, the number of downvotes is not significantly higher in videos with negative sentiment.

Physics-Informed Neural Networks (PINNs) are hybrid models that incorporate differential equations into the training of neural networks, with the aim of bringing the best of both worlds. This project used a mathematical model describing a Continuous Stirred-Tank Reactor (CSTR), to test two possible applications of PINNs. The first type of PINN was trained to predict an unknown reaction rate law, based only on the differential equation and a time series of the reactor state. The resulting model was used inside a multi-step solver to simulate the system state over time. The results showed that the PINN could accurately model the behaviour of the missing physics also for new initial conditions. However, the model suffered from extrapolation error when tested on a larger reactor, with a much lower reaction rate. Comparisons between using a numerical derivative or automatic differentiation in the loss equation, indicated that the latter had a higher robustness to noise. Thus, it is likely the best choice for real applications. A second type of PINN was trained to forecast the system state one-step-ahead based on previous states and other known model parameters. An ordinary feed-forward neural network with an equal architecture was used as baseline. The second type of PINN did not outperform the baseline network. Further studies are needed to conclude if or when physics-informed loss should be used in autoregressive applications.

Artificial neural networks are increasing in power, with attendant increases in demand for efficient processing. Performance is limited by clock speed and degree of parallelization available through multi-core processors and GPUs. With a design tailored to a specific network, a field-programmable gate array (FPGA) can be used to minimize latency without the need for geographically distributed computing. However, the task of programming an FPGA is outside the realm of most data scientists. There are tools to program FPGAs from a high level description of a network, but there is no unified interface for programmers across these tools. In this thesis, I present the design and implementation of NeuralSynth, a prototype Python framework which aims to bridge the gap between data scientists and FPGA programming for neural networks. My method relies on creating an extensible Python framework that is used to automate programming and interaction with an FPGA. The implementation includes a digital design for the FPGA that is completed by a Python framework. Programming and interacting with the FPGA does not require leaving the Python environment. The extensible approach allows multiple implementations, resulting in a similar workflow for each implementation. For evaluation, I compare the results of my implementation with a known neural network framework. / Includes bibliography. / Thesis (M.S.)--Florida Atlantic University, 2020. / FAU Electronic Theses and Dissertations Collection

Indiana University-Purdue University Indianapolis (IUPUI) / Action recognition has been an active research topic for over three decades. There are various applications of action recognition, such as surveillance, human-computer interaction, and content-based retrieval. Recently, research focuses on movies, web videos, and TV shows datasets. The nature of these datasets make action recognition very challenging due to scene variability and complexity, namely background clutter, occlusions, viewpoint changes, fast irregular motion, and large spatio-temporal search space (articulation configurations and motions). The use of local space and time image features shows promising results, avoiding the cumbersome and often inaccurate frame-by-frame segmentation (boundary estimation). We focus on two state of the art methods for the action classification problem: dense trajectories and recurrent neural networks (RNN). Dense trajectories use typical supervised training (e.g., with Support Vector Machines) of features such as 3D-SIFT, extended SURF, HOG3D, and local trinary patterns; the main idea is to densely sample these features in each frame and track them in the sequence based on optical flow. On the other hand, the deep neural network uses the input frames to detect action and produce part proposals, i.e., estimate information on body parts (shapes and locations). We compare qualitatively and numerically these two approaches, indicative to what is used today, and describe our conclusions with respect to accuracy and efficiency.

Indiana University-Purdue University Indianapolis (IUPUI) / Humans can visually see things and can differentiate objects easily but for computers, it is not that easy. Computer Vision is an interdisciplinary field that allows computers to comprehend, from digital videos and images, and differentiate objects. With the Introduction to CNNs/DNNs, computer vision is tremendously used in applications like ADAS, robotics and autonomous systems, etc. This thesis aims to propose an architecture, RMNv2, that is well suited for computer vision applications such as ADAS, etc. RMNv2 is inspired by its original architecture Mobilenet V2. It is a modified version of Mobilenet V2. It includes changes like disabling downsample layers, Heterogeneous kernel-based convolutions, mish activation, and auto augmentation. The proposed model is trained from scratch in the CIFAR10 dataset and produced an accuracy of 92.4% with a total number of parameters of 1.06M. The results indicate that the proposed model has a model size of 4.3MB which is like a 52.2% decrease from its original implementation. Due to its less size and competitive accuracy the proposed model can be easily deployed in resource-constrained devices like mobile and embedded devices for applications like ADAS etc. Further, the proposed model is also implemented in real-time embedded devices like NXP Bluebox 2.0 and NXP i.MX RT1060 for image classification tasks.

No description available.

No description available.

No description available.

No description available.