A review on dropout regularization approaches for deep neural networks within the scholarly domain
Dropout is one of the most popular regularization methods in the scholarly domain for
preventing a neural network model from overfitting in the training phase. Develo** an …
preventing a neural network model from overfitting in the training phase. Develo** an …
Resource-efficient algorithms and systems of foundation models: A survey
Large foundation models, including large language models, vision transformers, diffusion,
and large language model based multimodal models, are revolutionizing the entire machine …
and large language model based multimodal models, are revolutionizing the entire machine …
Which tokens to use? investigating token reduction in vision transformers
Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs
more efficient by removing redundant information in the processed tokens. While different …
more efficient by removing redundant information in the processed tokens. While different …
Compute-efficient deep learning: Algorithmic trends and opportunities
Although deep learning has made great progress in recent years, the exploding economic
and environmental costs of training neural networks are becoming unsustainable. To …
and environmental costs of training neural networks are becoming unsustainable. To …
A survey of resource-efficient llm and multimodal foundation models
Large foundation models, including large language models (LLMs), vision transformers
(ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine …
(ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine …
Learning probabilistic symmetrization for architecture agnostic equivariance
We present a novel framework to overcome the limitations of equivariant architectures in
learning functions with group symmetries. In contrary to equivariant architectures, we use an …
learning functions with group symmetries. In contrary to equivariant architectures, we use an …
Survey of different large language model architectures: Trends, benchmarks, and challenges
Large Language Models (LLMs) represent a class of deep learning models adept at
understanding natural language and generating coherent responses to various prompts or …
understanding natural language and generating coherent responses to various prompts or …
Frozen Feature Augmentation for Few-Shot Image Classification
Training a linear classifier or lightweight model on top of pretrained vision model outputs so-
called'frozen features' leads to impressive performance on a number of downstream few …
called'frozen features' leads to impressive performance on a number of downstream few …
GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation
Abstract Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their
deployments on resource-constrained devices remain challenging due to high …
deployments on resource-constrained devices remain challenging due to high …
ViTs as backbones: Leveraging vision transformers for feature extraction
Abstract The emergence of Vision Transformers (ViTs) has marked a significant shift in the
field of computer vision, presenting new methodologies that challenge traditional …
field of computer vision, presenting new methodologies that challenge traditional …