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 3 of 3 for “"network embeddings"”.

  1. Sequential decision making with feature-linear models

    … learning setting with features given by a neural network. The thesis is split into two parts accordingly. In part I, we introduce a new algorithm for the optimisation of continuous functions with a known number of derivatives under noisy bandit feedback. The algorithm, Partitioned GP-UCB, combines …

    cambridge Repository record for Sequential decision making with feature-linear models (opens in a new tab)

  2. Essays on Martech: Learning to Design, Deliver, and Diffuse Interventions

    … by fine-tuning a deep 3D convolutional neural network on video-level engagement data. M-score is then defined as pixel-level engagement-weighted advertising intensity of a video. The algorithm is constructed and evaluated with influencer video ads on TikTok. Causal effects of video ads on …

    mit Repository record for Essays on Martech: Learning to Design, Deliver, and Diffuse Interventions (opens in a new tab)

  3. The resurgence of structure in deep neural networks

    Machine learning with deep neural networks ("deep learning") allows for learning complex features directly from raw input data, completely eliminating hand-crafted, "hard-coded" feature extraction from the learning pipeline. This has lead to state-of-the-art performance being achieved across …

    cambridge Repository record for The resurgence of structure in deep neural networks (opens in a new tab)