Model-agnostic measure of generalization difficulty
A Boopathy, K Liu, J Hwang, S Ge… - International …, 2023 - proceedings.mlr.press
The measure of a machine learning algorithm is the difficulty of the tasks it can perform, and
sufficiently difficult tasks are critical drivers of strong machine learning models. However …
sufficiently difficult tasks are critical drivers of strong machine learning models. However …
Towards exact computation of inductive bias
Much research in machine learning involves finding appropriate inductive biases (eg
convolutional neural networks, momentum-based optimizers, transformers) to promote …
convolutional neural networks, momentum-based optimizers, transformers) to promote …
Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training
Deep neural networks have achieved great success in many data processing applications.
However, the high computational complexity and storage cost makes deep learning hard to …
However, the high computational complexity and storage cost makes deep learning hard to …
[PDF][PDF] Towards Sustainable CNNs: Tensor Decompositions for
AI Green, D Breen - repository.tudelft.nl
The ever-increasing complexity of Artificial Intelligence (AI) models has led to environmental
challenges due to high computation and energy demands. This thesis explores the …
challenges due to high computation and energy demands. This thesis explores the …