paper-with-me

홈 › Papers

Challenges and Opportunities in Approximate Bayesian Deep Learning for Intelligent IoT Systems

2021-12-03 · Meet P. Vadera, Benjamin M. Marlin

Approximate Bayesian deep learning methods hold significant promise for addressing several issues that occur when deploying deep learning components in intelligent systems, including mitigating the occurrence of over-confident errors and providing enhanced robustness to out of distribution examples. However, the computational requirements of existing approximate Bayesian inference methods can make them ill-suited for deployment in intelligent IoT systems that include lower-powered edge devices. In this paper, we present a range of approximate Bayesian inference methods for supervised deep learning and highlight the challenges and opportunities when applying these methods on current edge hardware. We highlight several potential solutions to decreasing model storage requirements and improving computational scalability, including model pruning and distillation methods.

📄 PDF Abstract BibTeX arXiv:2112.01675

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian InferenceDeep Learning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Bayes in the age of intelligent machines

2023-11-16 · Thomas L. Griffiths, Jian-Qiao Zhu, Erin Grant, R. Thomas McCoy

The success of methods based on artificial neural networks in creating intelligent machines seems like it might pose a challenge to explanations of human cognition in terms of Bayesian inference. We argue that this is no…

Bayesian Inference

UAVs with Reconfigurable Intelligent Surfaces: Applications, Challenges, and Opportunities

2020-12-08 · Aly Sabri Abdalla, Talha Faizur Rahman, Vuk Marojevic

A reconfigurable intelligent surface (RIS) is a metamaterial that can be integrated into walls and influence the propagation of electromagnetic waves. This, typically passive radio frequency (RF) technology is emerging f…

Bayesian optimization as a flexible and efficient design framework for sustainable process systems

2024-01-29 · Joel A. Paulson, Calvin Tsay

Bayesian optimization (BO) is a powerful technology for optimizing noisy expensive-to-evaluate black-box functions, with a broad range of real-world applications in science, engineering, economics, manufacturing, and bey…

Bayesian Optimization

Bayesian Optimization in Materials Science: A Survey

2021-07-29 · Lars Kotthoff, Hud Wahab, Patrick Johnson

Bayesian optimization is used in many areas of AI for the optimization of black-box processes and has achieved impressive improvements of the state of the art for a lot of applications. It intelligently explores large an…

Bayesian OptimizationSurvey

LLMs in Education: Novel Perspectives, Challenges, and Opportunities

2024-09-18 · Bashar Alhafni, Sowmya Vajjala, Stefano Bannò, Kaushal Kumar Maurya 외

The role of large language models (LLMs) in education is an increasing area of interest today, considering the new opportunities they offer for teaching, learning, and assessment. This cutting-edge tutorial provides an o…