paper-with-me

Papers

TensorBNN: Bayesian Inference for Neural Networks using Tensorflow

2020-09-30 · Braden Kronheim, Michelle Kuchera, Harrison Prosper

TensorBNN is a new package based on TensorFlow that implements Bayesian inference for modern neural network models. The posterior density of neural network model parameters is represented as a point cloud sampled using Hamiltonian Monte Carlo. The TensorBNN package leverages TensorFlow's architecture and training features as well as its ability to use modern graphics processing units (GPU) in both the training and prediction stages.

📄 PDF Abstract BibTeX arXiv:2009.14393

Code (1)

alpha-davidson/TensorBNN 공식 구현 tf

Tasks

Bayesian InferenceGPU

Similar Papers 제목 키워드 기반

Automatic Tuning of Tensorflow's CPU Backend using Gradient-Free Optimization Algorithms

2021-09-13 · Derssie Mebratu, Niranjan Hasabnis, Pietro Mercati, Gaurit Sharma 외

Modern deep learning (DL) applications are built using DL libraries and frameworks such as TensorFlow and PyTorch. These frameworks have complex parameters and tuning them to obtain good training and inference performanc…

Bayesian OptimizationCPU

ZhuSuan: A Library for Bayesian Deep Learning

2017-09-18 · Jiaxin Shi, Jianfei Chen, Jun Zhu, Shengyang Sun 외

In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Tensorfl…

Bayesian InferenceDeep LearningProbabilistic Programmingregression

Native Fortran Implementation of TensorFlow-Trained Deep and Bayesian Neural Networks

2025-02-07 · Aidan Furlong, Xingang Zhao, Bob Salko, Xu Wu

Over the past decade, the investigation of machine learning (ML) within the field of nuclear engineering has grown significantly. With many approaches reaching maturity, the next phase of investigation will determine the…

Computational Efficiency

Bayesian Neural Networks: Essentials

2021-06-22 · Daniel T. Chang

Bayesian neural networks utilize probabilistic layers that capture uncertainty over weights and activations, and are trained using Bayesian inference. Since these probabilistic layers are designed to be drop-in replaceme…

Bayesian InferenceProbabilistic Deep Learning

GPflowOpt: A Bayesian Optimization Library using TensorFlow

2017-11-10 · Nicolas Knudde, Joachim van der Herten, Tom Dhaene, Ivo Couckuyt

A novel Python framework for Bayesian optimization known as GPflowOpt is introduced. The package is based on the popular GPflow library for Gaussian processes, leveraging the benefits of TensorFlow including automatic di…

Bayesian OptimisationBayesian OptimizationGaussian ProcessesGPU