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 20 for “"Deep learning theory"”.

  1. Subsurface characterization using deep learning theory and techniques

    … available measurements. Additionally, a deep learning surrogate model is used for faster simulations. Chapter 3 applies the proposed data assimilation framework to CO2 storage sites characterization. Several subsurface site characterization examples including Gaussian, channelized, and …

    hawaii Repository record for Subsurface characterization using deep learning theory and techniques (opens in a new tab)

  2. Nonlinear and geometric control methods in deep learning theory

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-12-01

    uiuc Repository record for Nonlinear and geometric control methods in deep learning theory (opens in a new tab)

  3. Demystifying deep network architectures : from theory to applications

    Deep neural networks significantly power the success of machine learning and artificial intelligence. Over the past decade, the community keeps designing architectures of deep layers and complicated connections. Many works in deep learning theory tried to understand deep networks from different …

    texas Repository record for Demystifying deep network architectures : from theory to applications (opens in a new tab)

  4. Exploring the relationship between Deep Neural Networks and Neural Tangent Kernel via covariance manipulation

    … this study, we examine the relationship between Deep Neural Networks (DNNs) and the Neural Tangent Kernel (NTK), with a particular emphasis on covariance manipulation. Using the foundational framework provided by Roberts and Yaida in their book, "Deep Learning Theory," we methodically explore the …

    texas Repository record for Exploring the relationship between Deep Neural Networks and Neural Tangent Kernel via covariance manipulation (opens in a new tab)

  5. Towards Newtonian understanding of deep learning training dynamics

    Ever since the deep learning revolution, neural networks have been the dominating models in different machine learning areas such as computer vision, natural language processing, speech recognition. The wide application and success of deep learning in different areas have also lead to the evolution …

    texas Repository record for Towards Newtonian understanding of deep learning training dynamics (opens in a new tab)

  6. Machine Learning As Tool And Theory For Computational Neuroscience

    … brain based on the ideas and methods of machine learning. This is effort has been encouraged, in part, by recent advances in neural network models. It is also driven by a recognition of the complexity of neural computation and the challenges that this poses for neuroscience’s methods. In this …

    penn Repository record for Machine Learning As Tool And Theory For Computational Neuroscience (opens in a new tab)

  7. Testing theories of computation and learning in the visual cortex

    … coding. In the second study, we propose that learning dynamics – the evolving patterns of neural changes across time compared within and across areas – can serve as a crucial hallmark to test theories of learning in the brain. We devise a multi-stage behaviour and neuronal imaging paradigm in …

    oxford Repository record for Testing theories of computation and learning in the visual cortex (opens in a new tab)

  8. Understanding and Enhancing Machine Learning Models with Theoretical Foundations

    Machine learning has become a key driver of many contemporary technological advancements. With its empirical success, there is an urgent need for theoretical research to explain and complement these practical achievements. This includes understanding the empirical success of machine learning, …

    maryland Repository record for Understanding and Enhancing Machine Learning Models with Theoretical Foundations (opens in a new tab)

  9. Deep learning frameworks for modeling how neural circuits learn

    The brain's prowess in learning and adapting remains an enigma, particularly in its approach to the 'temporal credit assignment' problem. How do neural circuits determine which specific states and connections contribute to future outcomes, and subsequently adjust these for enhanced learning? My …

    washington Repository record for Deep learning frameworks for modeling how neural circuits learn (opens in a new tab)

  10. Learning with Distribution Shift: Theory and Practice

    … design and theoretical analysis in continual learning (CL), a machine learning paradigm where learning agents sequentially encounter tasks with distinct distributions. While state-of-the-art machine learning algorithms (e.g., deep neural networks) designed for single-task problems achieve …

    rice Repository record for Learning with Distribution Shift: Theory and Practice (opens in a new tab)

  11. Understanding Modern Machine Learning Models through the Llens of High-dimensional Statistics

    Deep neural networks have become an indispensable component of artificial intelligence as seen in a wide range of impressive applications, yet many of their properties remain mysterious. For instance, the non-convex loss landscape may conflict with efficient optimization by standard gradient-based …

    toronto-retro Repository record for Understanding Modern Machine Learning Models through the Llens of High-dimensional Statistics (opens in a new tab)

  12. Analysis of Learning Algorithms via Diffusion Limits

    Modern machine learning algorithms are often very difficult to analyze, as discrete units of scaling and time typically do not lead to very clean closed form representations. For example, updates can be in discrete time, and neural networks have finitely many distinct neurons per layer. In this …

    toronto-retro Repository record for Analysis of Learning Algorithms via Diffusion Limits (opens in a new tab)

  13. Uniform Sampling from Deep Generative Network Manifolds

    Deep Generative Networks (DGNs) are extensively employed to approximate data manifolds and distributions. However, samples used to train such DGNs are often distributed non-uniformly on the manifold, due to the cost or convenience of collection. For example, the CelebA dataset contains a large …

    rice Repository record for Uniform Sampling from Deep Generative Network Manifolds (opens in a new tab)

  14. Non-convex and Interactive Learning via Stochastic Optimization

    Advances in machine learning have led to many empirical breakthroughs in computer science, from developing state-of-the-art image classification models to defeating the world champion in the game of Go. From statistical learning (e.g. image recognition) to interactive learning (e.g. the game of …

    cornell Repository record for Non-convex and Interactive Learning via Stochastic Optimization (opens in a new tab)

  15. STATISTICAL AND HIGH-DIMENSIONAL PERSPECTIVES ON MACHINE LEARNING

    … calibration.While the accuracy of modern machine learning techniques continues to improve, many models exhibit mis-calibration, wherein the probability scores produced by the models fail to align with the actual frequencies of the labels. This discrepancy can lead to unreliable predictions and …

    penn Repository record for STATISTICAL AND HIGH-DIMENSIONAL PERSPECTIVES ON MACHINE LEARNING (opens in a new tab)

  16. STRUCTURED DATA ANALYSIS: MODELS, ALGORITHMS AND THEORIES

    … problems in computer vision and machine learning becomes very important. This thesis addresses this problem from three aspects: (1) designing effective structured data learning models, (2) developing efficient optimization algorithms, and (3) establishing solid theory to understand …

    nus Repository record for STRUCTURED DATA ANALYSIS: MODELS, ALGORITHMS AND THEORIES (opens in a new tab) Download file for STRUCTURED DATA ANALYSIS: MODELS, ALGORITHMS AND THEORIES (opens in a new tab)

  17. Understanding Deep Learning via Tractable Models

    Deep learning systems have transformed information processing, achieving remarkable success in domains ranging from computer vision to natural language processing, and are completely reshaping every sector of the industry. Yet, our theoretical understanding of why these systems work lags far behind …

    penn Repository record for Understanding Deep Learning via Tractable Models (opens in a new tab)

  18. The Angle Degeneracy Phenomenon in Deep Neural Networks: Analysis and Relation to Training Dynamics

    Deep neural networks have proven to be powerful functions with many applications, but the theoretical behaviour of these functions is not fully understood. One such behaviour is the large depth degeneracy phenomenon, where inputs tend to become highly correlated as they travel deeper into a …

    guelph Repository record for The Angle Degeneracy Phenomenon in Deep Neural Networks: Analysis and Relation to Training Dynamics (opens in a new tab)