Results 11 to 20 of about 4,010,683 (211)

Explanations for Neural Networks by Neural Networks [PDF]

open access: yesApplied Sciences, 2022
Understanding the function learned by a neural network is crucial in many domains, e.g., to detect a model’s adaption to concept drift in online learning. Existing global surrogate model approaches generate explanations by maximizing the fidelity between the neural network and a surrogate model on a sample-basis, which can be very time-consuming ...
Sascha Marton   +2 more
openaire   +2 more sources

Neural Networks With Motivation [PDF]

open access: yesFrontiers in Systems Neuroscience, 2021
Animals rely on internal motivational states to make decisions. The role of motivational salience in decision making is in early stages of mathematical understanding. Here, we propose a reinforcement learning framework that relies on neural networks to learn optimal ongoing behavior for dynamically changing motivation values. First, we show that neural
Sergey A. Shuvaev   +5 more
openaire   +6 more sources

Medical imaging analysis with artificial neural networks [PDF]

open access: yes, 2010
Given that neural networks have been widely reported in the research community of medical imaging, we provide a focused literature survey on recent neural network developments in computer-aided diagnosis, medical image segmentation and edge detection ...
Jiang, J., Ren, Jinchang, Trundle, P.
core   +4 more sources

Neural network approximation [PDF]

open access: yesActa Numerica, 2021
Neural networks (NNs) are the method of choice for building learning algorithms. They are now being investigated for other numerical tasks such as solving high-dimensional partial differential equations. Their popularity stems from their empirical success on several challenging learning problems (computer chess/Go, autonomous navigation, face ...
Ronald A. DeVore   +2 more
openaire   +4 more sources

Analyzing Echo-state Networks Using Fractal Dimension [PDF]

open access: yes, 2022
This work joins aspects of reservoir optimization, information-theoretic optimal encoding, and at its center fractal analysis. We build on the observation that, due to the recursive nature of recurrent neural networks, input sequences appear as fractal ...
Obst, Oliver   +3 more
core   +1 more source

Operational neural networks [PDF]

open access: yesNeural Computing and Applications, 2020
AbstractFeed-forward, fully connected artificial neural networks or the so-called multi-layer perceptrons are well-known universal approximators. However, their learning performance varies significantly depending on the function or the solution space that they attempt to approximate. This is mainly because of their homogenous configuration based solely
Serkan Kiranyaz   +3 more
openaire   +6 more sources

Lazy training of radial basis neural networks [PDF]

open access: yes, 2006
Proceeding of: 16th International Conference on Artificial Neural Networks, ICANN 2006. Athens, Greece, September 10-14, 2006Usually, training data are not evenly distributed in the input space.
Galván, Inés M.   +5 more
core   +1 more source

Evolutionary cellular configurations for designing feed-forward neural networks architectures [PDF]

open access: yes, 2001
Proceeding of: 6th International Work-Conference on Artificial and Natural Neural Networks, IWANN 2001 Granada, Spain, June 13–15, 2001In the recent years, the interest to develop automatic methods to determine appropriate architectures of feed-forward ...
Gutiérrez Sánchez, Germán   +6 more
core   +1 more source

Approximation in shift-invariant spaces with deep ReLU neural networks [PDF]

open access: yes, 2022
We study the expressive power of deep ReLU neural networks for approximating functions in dilated shift-invariant spaces, which are widely used in signal processing, image processing, communications and so on.
Wang, Yang, Li, Zhen, Yang, Yunfei
core   +1 more source

In-network Neural Networks

open access: yesCoRR, 2018
We present N2Net, a system that implements binary neural networks using commodity switching chips deployed in network switches and routers. Our system shows that these devices can run simple neural network models, whose input is encoded in the network packets' header, at packet processing speeds (billions of packets per second).
Giuseppe Siracusano, Roberto Bifulco
openaire   +2 more sources

Home - About - Disclaimer - Privacy