Results 31 to 40 of about 227,027 (269)

Advanced obstacle avoidance for a laser based wheelchair using optimised Bayesian neural networks. [PDF]

, 2008
In this paper we present an advanced method of obstacle avoidance for a laser based intelligent wheelchair using optimized Bayesian neural networks. Three neural networks are designed for three separate sub-tasks: passing through a door way, corridor and
Nguyen, HT, Trieu, HT, Willey, K
core   +1 more source

Bayesian Neural Networks

, 2018
This paper describes and discusses Bayesian Neural Network (BNN). The paper showcases a few different applications of them for classification and regression problems. BNNs are comprised of a Probabilistic Model and a Neural Network. The intent of such a design is to combine the strengths of Neural Networks and Stochastic modeling.
Mullachery, Vikram, Khera, Aniruddh, Husain, Amir   +2 more
openaire   +2 more sources

Bayesian Graph Convolutional Neural Networks via Tempered MCMC

IEEE Access, 2021
Deep learning models, such as convolutional neural networks, have long been applied to image and multi-media tasks, particularly those with structured data.
Rohitash Chandra, Ayush Bhagat, Manavendra Maharana, Pavel N. Krivitsky   +3 more
doaj   +1 more source

Spatial Bayesian neural networks

Spatial Statistics
35 pages, 21 ...
Andrew Zammit-Mangion, Michael D. Kaminski, Ba-Hien Tran, Maurizio Filippone, Noel Cressie   +4 more
openaire   +3 more sources

Bayesian Neural Networks for Sparse Coding [PDF]

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
Deep learning is actively used in the area of sparse coding. In current deep sparse coding methods uncertainty of predictions is rarely estimated, thus providing the results that lack the quantitative justification. Bayesian learning provides the way to estimate the uncertainty of predictions in neural networks (NNs) by imposing the prior distributions
Kuzin, D., Isupova, O., Mihaylova, L.
openaire   +2 more sources

Ex Situ Transfer of Bayesian Neural Networks to Resistive Memory‐Based Inference Hardware

Advanced Intelligent Systems, 2021
Neural networks cannot typically be trained locally in edge‐computing systems due to severe energy constraints. It has, therefore, become commonplace to train them “ex situ” and transfer the resulting model to a dedicated inference hardware.
Thomas Dalgaty, Eduardo Esmanhotto, Niccolo Castellani, Damien Querlioz, Elisa Vianello   +4 more
doaj   +1 more source

Confident Classification Using a Hybrid Between Deterministic and Probabilistic Convolutional Neural Networks

IEEE Access, 2020
Traditional neural networks trained using point-based maximum likelihood estimation are deterministic models and have exhibited near-human performance in many image classification tasks.
Muhammad Naseer Bajwa, Suleman Khurram, Mohsin Munir, Shoaib Ahmed Siddiqui, Muhammad Imran Malik, Andreas Dengel, Sheraz Ahmed   +6 more
doaj   +1 more source

Using topological data analysis for building Bayesan neural networks

Научно-технический вестник информационных технологий, механики и оптики
For the first time, a simplified approach to constructing Bayesian neural networks is proposed, combining computational efficiency with the ability to analyze the learning process.
A. S. Vatian, N. F. Gusarova, D. A. Dobrenko, K. S. Pankova, I. V. Tomilov   +4 more
doaj   +1 more source

Improved Uncertainty Quantification for Neural Networks With Bayesian Last Layer

IEEE Access, 2023
Uncertainty quantification is an important task in machine learning - a task in which standard neural networks (NNs) have traditionally not excelled. This can be a limitation for safety-critical applications, where uncertainty-aware methods like Gaussian
Felix Fiedler, Sergio Lucia
doaj   +1 more source

Scaling Up Bayesian Neural Networks with Neural Networks

, 2023
25 ...
Moslemi, Zahra, Meng, Yang, Lan, Shiwei, Shahbaba, Babak   +3 more
openaire   +2 more sources