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 10 of 10 for “"Parameter efficiency"”.
-
Advances in Few-Shot Learning for Image Classification and Tabular Data
… require updating only a small fraction of model parameters for adaptation -- a crucial form of parameter efficiency -- to enable low-cost personalisation, enhance communication-efficiency in federated learning, and potentially mitigate catastrophic forgetting in adapted systems. In this thesis, …
-
TOWARDS EFFICIENT TRANSFORMER SCALING
… explores strategies to enhance Transformer efficiency. First, we propose WideNet, which optimizes parameter efficiency using parameter-sharing and Mixture-of-Experts, achieving strong results in both vision and language tasks. Second, we investigate transformer configurations, finding that …
-
Achieving More with Less: Learning Generalizable Neural Networks With Less Labeled Data and Computational Overheads
… devices. This dissertation aims to improve efficiency in machine learning by exploring different ways to learn generalizable neural networks that require less labeled data and computational resources. We demonstrate that using physics supervision in scientific problems can reduce the need …
-
Interpretable Deep Image Denoiser by Unrolling Graph Laplacian Regularizer
… but these models require on large numbers of parameters, lack interpretability, and depend heavily on random parameter initialization. As a result, they frequently converge to poor-performing local minima. This thesis proposes an image denoising neural net constructed by unrolling an iterative …
-
Encoding parameter and structural efficiency in deep learning
… power, which allows for deep and highly parameterized neural network architectures which can learn complex feature transformations from raw data. The high representational power of deep neural networks, however, often comes at the cost of high model complexity which refers to the high …
-
On the Resource Efficiency of Language Models
… resource challenges in two dimensions: data efficiency and model efficiency. For post-training, LLMs face data curation challenges where high-quality labeled data is scarce and expensive to obtain, and data utilization challenges where existing methods fail to optimize model performance on …
-
On Principled Modeling of Inductive Bias in Machine Learning
… large language models). To further improve the parameter efficiency, we also develop a new parameterization using butterfly factorization. In data-centric modeling, we introduce the iterative machine teaching framework for studying the effect of training data manipulation on inductive bias. …
-
Deep Memory Models and Efficient Reinforcement Learning under Partial Observability
… graph of memories on the fly, improving data and parameter efficiency when compared with standard memory models. Next, we discuss a large scale study of memory models. We design a variety of procedurally generated tasks, and then implement and evaluate an array of memory models on these tasks. …
-
Eclipse: a feedback-driven framework and automated quality assessment system for reliable, interpretable, and multi-modal biomedical AI
… dimensions: Novelty, Architecture Complexity, Parameter Efficiency, Hardware Resource Characterization, Scalability, Generalizability, and Adaptability) under the composite MERIT-C = α · RQSₙₒᵣₘ + β · TAMSₙₒᵣₘ. Validated against 89 peer-review scores from OpenReview (Spearman ρ = 0.346, p = …
-
Deep learning for image restoration and enhancement
… its neighborhood. We fully use an RNN for its parameter efficiency and allow deep feature correlation to be propagated along adjacent recurrent states. This design boosts robustness against inaccurate correlation estimation due to severely degraded images. Finally, we show that it is essential …