Results 231 to 240 of about 127,617 (265)
Some of the next articles are maybe not open access.
Proceedings of the 5th International Conference on Control Engineering and Artificial Intelligence, 2021
In recent years, deep convolutional neural networks (CNNs) have achieved great success in computer vision tasks. However, they are often perceived as "black box" methods for the lack of interpretability. In this work, we propose an approach to alleviate the opaqueness of deep learning models by providing visual explanations to the predictions of the ...
Yuhan Dong +5 more
openaire +1 more source
In recent years, deep convolutional neural networks (CNNs) have achieved great success in computer vision tasks. However, they are often perceived as "black box" methods for the lack of interpretability. In this work, we propose an approach to alleviate the opaqueness of deep learning models by providing visual explanations to the predictions of the ...
Yuhan Dong +5 more
openaire +1 more source
IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020
We extend backpropagation (BP) learning from ordinary unidirectional training to bidirectional training of deep multilayer neural networks. This gives a form of backward chaining or inverse inference from an observed network output to a candidate input that produced the output.
Olaoluwa Adigun, Bart Kosko
openaire +1 more source
We extend backpropagation (BP) learning from ordinary unidirectional training to bidirectional training of deep multilayer neural networks. This gives a form of backward chaining or inverse inference from an observed network output to a candidate input that produced the output.
Olaoluwa Adigun, Bart Kosko
openaire +1 more source
Kybernetes, 2001
The popular backpropagation algorithm for training neural nets is a special case of an earlier principle of significance feedback, which in turn has much in common with Selfridge’s “Pandemonium” and a connection with McCulloch’s “redundancy of potential command”.
openaire +1 more source
The popular backpropagation algorithm for training neural nets is a special case of an earlier principle of significance feedback, which in turn has much in common with Selfridge’s “Pandemonium” and a connection with McCulloch’s “redundancy of potential command”.
openaire +1 more source
Journal of Organizational and End User Computing, 1999
The vast majority of neural network research relies on a gradient algorithm, typically a variation of backpropagation, to obtain the weights of the model. Because of the enigmatic nature of complex nonlinear optimization problems, such as training artificial neural networks, this technique has often produced inconsistent and unpredictable results.
Randall S. Sexton +2 more
openaire +1 more source
The vast majority of neural network research relies on a gradient algorithm, typically a variation of backpropagation, to obtain the weights of the model. Because of the enigmatic nature of complex nonlinear optimization problems, such as training artificial neural networks, this technique has often produced inconsistent and unpredictable results.
Randall S. Sexton +2 more
openaire +1 more source
ACM Transactions on Graphics, 2020
Physically based differentiable rendering has recently evolved into a powerful tool for solving inverse problems involving light. Methods in this area perform a differentiable simulation of the physical process of light transport and scattering to estimate partial derivatives relating scene parameters to pixels in the rendered image.
Merlin Nimier-David +3 more
openaire +1 more source
Physically based differentiable rendering has recently evolved into a powerful tool for solving inverse problems involving light. Methods in this area perform a differentiable simulation of the physical process of light transport and scattering to estimate partial derivatives relating scene parameters to pixels in the rendered image.
Merlin Nimier-David +3 more
openaire +1 more source
Multifrequency Holography Using Backpropagation
Ultrasonic Imaging, 1986The technique of wavefield backpropagation has been used quite extensively in the literature. We report on an analytical study of the resolution properties of this technique. Backpropagation as a form of holographic reconstruction suffers from poor axial resolution. We derive expressions for both the axial and the lateral resolutions.
T J, Teo, J M, Reid
openaire +2 more sources
ACM Transactions on Graphics, 2021
Differentiable physically-based rendering has become an indispensable tool for solving inverse problems involving light. Most applications in this area jointly optimize a large set of scene parameters to minimize an objective function, in which case reverse-mode differentiation is the method of choice for obtaining parameter gradients ...
Delio Vicini +2 more
openaire +1 more source
Differentiable physically-based rendering has become an indispensable tool for solving inverse problems involving light. Most applications in this area jointly optimize a large set of scene parameters to minimize an objective function, in which case reverse-mode differentiation is the method of choice for obtaining parameter gradients ...
Delio Vicini +2 more
openaire +1 more source
Contrast enhancement for backpropagation
IEEE Transactions on Neural Networks, 1996This paper analyzes the effect of data-contrast to a backpropagation (BP) network and introduces a data preprocessing algorithm that can improve the efficiency of the standard BP learning. The basic idea is to transform input data to a range that associates the high-slope region of the sigmoid function where a relatively large modification of weights ...
T M, Kwon, H, Cheng
openaire +2 more sources
Quick fuzzy backpropagation algorithm
Neural Networks, 2001A modification of the fuzzy backpropagation (FBP) algorithm called QuickFBP algorithm is proposed, where the computation of the net function is significantly quicker. It is proved that the FBP algorithm is of exponential time complexity, while the QuickFBP algorithm is of polynomial time complexity. Convergence conditions of the QuickFBP, resp. the FBP
A, Nikov, S, Stoeva
openaire +2 more sources
Incremental backpropagation learning networks
IEEE Transactions on Neural Networks, 1996How to learn new knowledge without forgetting old knowledge is a key issue in designing an incremental-learning neural network. In this paper, we present a new incremental learning method for pattern recognition, called the "incremental backpropagation learning network", which employs bounded weight modification and structural adaptation learning rules
L, Fu, H H, Hsu, J C, Principe
openaire +2 more sources