1 code implementation • 20 Jan 2022 • Zachary Hamida, Blanche Laurent, James-A. Goulet
This paper describes OpenIPDM software for modelling the deterioration process of infrastructures using network-scale visual inspection data.
no code implementations • 8 Jul 2021 • Luong-Ha Nguyen, James-A. Goulet
With few exceptions, neural networks have been relying on backpropagation and gradient descent as the inference engine in order to learn the model parameters, because the closed-form Bayesian inference for neural networks has been considered to be intractable.
no code implementations • NeurIPS 2021 • Luong Ha, Nguyen, James-A. Goulet
In this paper, we present how we can adapt the temporal difference Q-learning framework to make it compatible with the tractable approximate Gaussian inference (TAGI), which allows learning the parameters of a neural network using a closed-form analytical method.
no code implementations • 9 Mar 2021 • Luong-Ha Nguyen, James-A. Goulet
Since its inception, deep learning has been overwhelmingly reliant on backpropagation and gradient-based optimization algorithms in order to learn weight and bias parameter values.
1 code implementation • Journal of Machine Learning Research 2021 • James-A. Goulet, Luong Ha Nguyen, Saeid Amiri
In this paper, we propose an analytical method for performing tractable approximate Gaussian inference (TAGI) in Bayesian neural networks.
no code implementations • 17 Apr 2015 • James-A. Goulet
This paper presents the Nataf-Beta Random Field Classifier, a discriminative approach that extends the applicability of the Beta conjugate prior to classification problems.