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 12 of 12 for “"residual networks"”.
-
Large-scale acoustic scene analysis with deep residual networks
Many of the recent advances in audio event detection, particularly on the AudioSet dataset, have focused on improving performance using the released embeddings produced by a pre-trained model. In this work, we instead study the task of training a multi-label event classifier directly from the audio …
-
Towards understanding residual neural networks
Residual networks (ResNets) are now a prominent architecture in the field of deep learning. However, an explanation for their success remains elusive. The original view is that residual connections allows for the training of deeper networks, but it is not clear that added layers are always useful, …
-
FEDERATED LEARNING OF BAYESIAN NEURAL NETWORKS
Although federated learning and Bayesian neural networks have been researched, there are few implementations of the federated learning of Bayesian networks. In this thesis, a federated learning training environment for Bayesian neural networks using a public code base, Flower, is developed. With it …
-
Topics in non-convex optimization and learning
… Riemannian optimization and deep neural networks. In the first part, I develop iteration complexity analysis for Riemannian optimization, i.e., optimization problems defined on Riemannian manifolds. Through bounding the distortion introduced by the metric curvature, iteration complexity …
-
AI-ML Powered Pig Behavior Classification and Body Weight Prediction
… learning (DL) solutions. Among these, the 2D Residual Networks emerged as the best performing model, achieving an accuracy of 95.6%. This accuracy was 15.6% higher than that of other machine learning approaches. Additionally, accurate pig weight estimation is crucial for pork production, as it …
-
The Deep Rendering Model: Bridging Theory and Practice in Deep Learning
… one, we can recover deep convolutional neural networks (DCNs) as well as its variants including the deep residual networks (ResNet) and the densely connected convolutional networks (DenseNet), providing insights into their successes and shortcomings as well as a principled route to their …
-
Quantitative convergence analysis of dynamical processes in machine learning
… performance of different architectures, deep residual networks (ResNets), and deep feedforward networks (FFNets). By taking these architectures as iterative maps and analyzing their convergence via neural tangent kernel, we prove that deep ResNets can effectively separate data while deep …
-
Power efficient machine learning-based hardware architectures for biomedical applications
… such as feedforward, convolutional neural nets, residual networks, and other popular machine learning and deep neural networks, are selected to benchmark the proposed model architecture. Various deep compression learning techniques, such as pruning, n-bit (n = 8,16) integer quantization, and …
-
The Force Floor: Design and Development of a Low-Cost 3D Force Sensing Area Which Utilises Machine Learning to Estimate 3D GRF and CoP from Single-Axis Loadcells
… Sim2Real transfer learning and physicsinformed residual networks. A data creation rig was built for purpose. Twenty prototype plates were built, with sixteen of them being interlinked to create the prototype Force Floor - a large force sensing area. The performance of a subset of these plates …
-
Application of capsule networks for image classification on complex datasets
… of this research is the introduction of residual blocks of primary capsule layers. We developed a novel architecture for CIFAR10 classification, called ResCapsNet, and find that the model increases validation accuracy to 78.54% from 71.04% achieved by the baseline CapsNet, at the marginal …
-
Are Particle-Based Methods the Future of Sampling in Joint Energy Models? A Deep Dive into SVGD and SGLD
This thesis investigates the integration of Stein Variational Gradient Descent (SVGD) with Joint Energy Models (JEMs), comparing its performance to Stochastic Gradient Langevin Dynamics (SGLD). We incorporated a generative loss term with an entropy component to enhance diversity and a smoothing …
-
Machine learning and combinatorial methods for discrete optimization problems
… duration distributions and larger problem sizes. Networks are an integral part of modern life, forming the backbone of the countless systems on which we rely daily. Network flow models cover a wide range of real-world applications; however, in many cases, splitting a commodity across multiple …