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 8 of 8 for “"Machine Learning Benchmarks"”.

  1. Applications of Computational Geometry and Computer Vision

    Recent advances in machine learning research promise to bring us closer to the original goals of artificial intelligence. Spurred by recent innovations in low-cost, specialized hardware and incremental refinements in machine learning algorithms, machine learning is revolutionizing entire …

    central-wash Repository record for Applications of Computational Geometry and Computer Vision (opens in a new tab)

  2. Essays on the Decision Value of Data in Marketing Measurement and Targeting

    … value achieved by non-privacy-preserving machine learning benchmarks. Together, the three essays characterize when data is helpful for personalization and marketing measurement, when it is not, and how data collection can be redesigned to improve its decision value.

    penn Repository record for Essays on the Decision Value of Data in Marketing Measurement and Targeting (opens in a new tab)

  3. Adapting deep neural networks as models of human visual perception

    … perception: (1) deep representational distance learning (RDL), a method for driving representational spaces in deep nets into alignment with other (e.g. brain) representational spaces and (2) variational DNNs that use sampling to perform approximate Bayesian inference. In the first …

    cambridge Repository record for Adapting deep neural networks as models of human visual perception (opens in a new tab)

  4. Sculpting representations for deep learning

    In machine learning, the choice of space in which to represent our data is of vital importance to their effective and efficient analysis. In this thesis, we develop approaches to address a number of problems in representation learning. We employ deep learning as means of sculpting our …

    mit Repository record for Sculpting representations for deep learning (opens in a new tab)

  5. Decision Making for Populations

    … large heterogeneous populations by privately learning from decentralized data sources. First, we introduce DeepABM a framework for Scalable, Fast and Differentiable Agent-based Modeling. DeepABM can simulate million-size populations in a few seconds on personal computers (up to 300x faster …

    mit Repository record for Decision Making for Populations (opens in a new tab)

  6. A comparative study of recurrent neural networks and statistical techniques for forecasting the stock prices of JSE-listed securities

    As machine learning has developed, the attention of stock price forecasters has slowly shifted from traditional statistical forecasting techniques towards machine learning techniques. This study investigated whether machine learning techniques, in particular, recurrent neural networks, do indeed …

    cape-town Repository record for A comparative study of recurrent neural networks and statistical techniques for forecasting the stock prices of JSE-listed securities (opens in a new tab)

  7. Towards externally valid machine learning: A spurious correlations perspective

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-08-01

    uiuc Repository record for Towards externally valid machine learning: A spurious correlations perspective (opens in a new tab)

  8. Toward effective and generalisable machine learning for biosignal time series

    … thesis addresses these challenges by developing machine learning methods tailored for biosignal time series that focus on self-supervised representation learning, domain adaptation, and foundation modelling for generalisation across tasks and datasets. We demonstrate the efficacy of these methods …

    cambridge Repository record for Toward effective and generalisable machine learning for biosignal time series (opens in a new tab)