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 9 of 9 for “"Neural tangent kernel"”.

  1. Testing, Learning, and Optimization in High Dimensions

    … for optimization and generalization of deep neural networks beyond their linear approximation. For the first problem, we characterize the optimal sample complexity up to logarithmic factors by proposing almost matching upper and lower bounds. For the second problem, we propose a new regime …

    mit Repository record for Testing, Learning, and Optimization in High Dimensions (opens in a new tab)

  2. Beneficial Initializations in Over-Parameterized Machine Learning Problems

    … we present an approach for transfer learning in kernel regression. Namely, we demonstrate that transfer learning corresponds to adding a function to the minimum norm solution that produces zero error on the training data. We use this approach to perform transfer learning on image classification …

    mit Repository record for Beneficial Initializations in Over-Parameterized Machine Learning Problems (opens in a new tab)

  3. Contextual Bandits with Neural Networks and Trees

    … τα νευρωνικά δίκτυα, συμπεριλαμ- βανομένου του Neural Tangent Kernel (NTK). Τέλος, η εργασία συνοψίζει τις βασικές ιδέες ορισμένων εμβληματικών ερ- γασιών, στις οποίες οι στατιστικές μέθοδοι αυτές χρησιμοποιήθηκαν για την προσέγγιση της συνάρτησης πλαισίου-ανταμοιβής στα contextual bandits.

    athens Repository record for Contextual Bandits with Neural Networks and Trees (opens in a new tab)

  4. An Empirical and Theoretical Analysis of the Role of Depth in Convolutional Neural Networks

    While over-parameterized neural networks are capable of perfectly fitting (interpolating) training data, these networks often perform well on test data, thereby contradicting classical learning theory. Recent work provided an explanation for this phenomenon by introducing the double descent curve, …

    mit Repository record for An Empirical and Theoretical Analysis of the Role of Depth in Convolutional Neural Networks (opens in a new tab)

  5. Theory and Applications of Matrix Completion in Genomics Datasets

    … empirical results for use of the novel Neural Tangent Kernel (NTK) in matrix completion. We derive the functional form of the NTK for a single-hidden-layer, infinite-width neural network with ReLU activation, and develop a framework applying the NTK to matrix completion. We explore a …

    mit Repository record for Theory and Applications of Matrix Completion in Genomics Datasets (opens in a new tab)

  6. Quantitative convergence analysis of dynamical processes in machine learning

    … maps and analyzing their convergence via neural tangent kernel, we prove that deep ResNets can effectively separate data while deep FFNets degenerate and lose their learnability.

    gatech Repository record for Quantitative convergence analysis of dynamical processes in machine learning (opens in a new tab)

  7. Foundations of Machine Learning: Over-parameterization and Feature Learning

    … two core principles driving the success of neural networks: over-parameterization and feature learning. We leverage these principles to design models with improved performance and interpretability on various computer vision and biomedical applications. We begin by discussing the benefits of …

    mit Repository record for Foundations of Machine Learning: Over-parameterization and Feature Learning (opens in a new tab)

  8. 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)

  9. Priors in finite and infinite Bayesian convolutional neural networks

    Bayesian neural networks (BNNs) have undergone many changes since the seminal work of Neal [Nea96]. Advances in approximate inference and the use of GPUs have scaled BNNs to larger data sets, and much higher layer and parameter counts. Yet, the priors used for BNN parameters have remained …

    cambridge Repository record for Priors in finite and infinite Bayesian convolutional neural networks (opens in a new tab)