A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search
[article]
2018
arXiv
pre-print
Preserved Fulltext
We formulate this problem as a neural architecture search problem and propose a novel differentiable neural architecture search (DNAS) framework to efficiently explore its exponential search space with ...
Recent work in network quantization has substantially reduced the time and space complexity of neural network inference, enabling their deployment on embedded and mobile devices with limited computational ...
The idea of super net and stochastic super net is also used in Saxena & Verbeek (2016) ; Veniat & Denoyer (2017) to explore macro architectures of neural nets. ...
arXiv:1812.00090v1
fatcat:twg7dl7xjnc7niukbyw2coip5m
Extending LOUPE for K-space Under-sampling Pattern Optimization in Multi-coil MRI
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
k-space sampling, rather than approximate stochastic k-space sampling of LOUPE during training, was applied together with a straight-through (ST) estimator to estimate the gradient of the threshold operation ...
in a neural network; thirdly, modified unrolled optimization network, rather than modified U-Net in LOUPE, was used as the reconstruction network in order to reconstruct multi-coil data properly and reduce ...
Thirdly, approximate stochastic sampling layer was replaced by a binary stochastic sampling layer with Straight-Through (ST) estimator [3] , which was used to avoid zero gradients when back-propagating ...
arXiv:2007.14450v1
fatcat:mkwqlddxg5b77geht6io3fulkm
On the approximation of the inverse dynamics of a robotic manipulator by a neural network trained with a stochastic learning algorithm
2013
Inge-Cuc
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Segura, "On the Approximation of the Inverse Dynamics of a Robotic Manipulator by a Neural Network Trained with a Stochastic Learning Algorithm", inge cuc, vol. 9, no. 2, pp. 39-43, 2013. ...
The neural net has the form for i = 1,2, being and Here we show some results obtained for the case of . Figure 3 shows the evolution of the mean relative error for independent training sets. ...
doaj:4745ddfd81e942eabbd159e6d340a73d
fatcat:6eotwatv7fdznnbjn2xh6vkauq
Computational promise of simultaneous recurrent network with a stochastic search mechanism
2004
2004 IEEE International Joint Conference on Neural Networks (IEEE Cat No 04CH37541) IJCNN-04
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2006; you can also visit the original URL.
The file type is application/pdf.
Successful application of Simultaneous Recurrent Neural networks to static optimization problems, where the training had been achieved through one of a number of deterministic gradient descent algorithms ...
Two techniques are employed to assess the added value of a potential enhancement through a stochastic search mechanism: one method entails comparison of SRN performance with a stochastic search algorithm ...
ACKNOWLEDGEMENT Partial Funding provided through United States National Science Foundation (NSF) Grant (ECS 98-00247) for this research project is gratefully acknowledged. ...
doi:10.1109/ijcnn.2004.1380969
fatcat:5cvava5w6rddddjodp54zrbimu
An Image Classification Method Based on Deep Neural Network with Energy Model
2018
CMES - Computer Modeling in Engineering & Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Stochastic depth network can successfully address these problems [Huang, Sun, Liu et al. (2016) ], it can greatly increase the nets depth and bring substantial performance than former networks. ...
In this paper, we propose a new algorithm called stochastic depth networks with deep energy model (SADIE), and the model improves stochastic depth neural network with deep energy model to provide attributes ...
But deep neural network based on energy model can train the nets as a whole and characterize the data features through hidden layers. ...
doi:10.31614/cmes.2018.04249
fatcat:vytorzfmabhktgocq2mhy7wto4
A Selective Overview of Deep Learning
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To answer these questions, we introduce common neural network models (e.g., convolutional neural nets, recurrent neural nets, generative adversarial nets) and training techniques (e.g., stochastic gradient ...
While neural networks have a long history, recent advances have greatly improved their performance in computer vision, natural language processing, etc. ...
This minimization is usually done via stochastic gradient descent (SGD). ...
arXiv:1904.05526v2
fatcat:6b2nhrmnsnezbowhahkue637fq
Learning to Optimize Neural Nets
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
More specifically, we show that an optimization algorithm trained with the proposed method on the problem of training a neural net on MNIST generalizes to the problems of training neural nets on the Toronto ...
In this paper, we explore learning an optimization algorithm for training shallow neural nets. ...
neural net. ...
arXiv:1703.00441v2
fatcat:dbz5bj57lve33ko2ninpyju4xe
A comparison of two optimization techniques for sequence discriminative training of deep neural networks
2014
2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We compare two optimization methods for lattice-based sequence discriminative training of neural network acoustic models: distributed Hessian-free (DHF) and stochastic gradient descent (SGD). ...
Our findings on two different LVCSR tasks suggest that SGD running on a single GPU machine achieves the best accuracy 2.5 times faster than DHF running on multiple non-GPU machines; however, DHF training ...
The criterion of choice for training neural nets for classification is cross-entropy. ...
doi:10.1109/icassp.2014.6854668
dblp:conf/icassp/SaonS14
fatcat:n2pkpf42k5az3jakxgcwrcpc7i
Binary Neural Networks: A Survey
2020
Pattern Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2004.03333v1 fatcat:g66mdapihrctrildkpcw6eyg2m
We also investigate other practical aspects of binary neural networks such as the hardware-friendly design and the training tricks. ...
In this paper, we present a comprehensive survey of these algorithms, mainly categorized into the native solutions directly conducting binarization, and the optimized ones using techniques like minimizing ...
In [61] , the Learned Quantization (LQ-Nets) attempts to minimize quantization error by jointly training neural networks and quantizers in the network. ...
doi:10.1016/j.patcog.2020.107281
fatcat:p7ohjigozza5viejq6x7cyf6zi
A Numerical Investigation of the Minimum Width of a Neural Network
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Through numerical experiments, we seek to test the lower bounds established by Hanin in 2017. ...
Neural network width and depth are fundamental aspects of network topology. ...
For every width, 10 distinct neural networks (depths 1 through 10) were created to numerically test Hanin's result. ...
arXiv:1910.13817v1
fatcat:ueciu2ps5bgfjon3fucrzipifa
Page 53 of Geographical Analysis Vol. 28, Issue 1
[page]
1996
Geographical Analysis
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
neural net compared to 0.7821 for the gravity model). ...
This functional form is modified via the adaptive setting of weights by means of the application of a local learning process that minimizes an error function through an iterative statistical scheme. ...
The "wake-sleep" algorithm for unsupervised neural networks
1995
Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2005; you can also visit the original URL.
The file type is application/pdf.
An unsupervised learning algorithm for a multilayer network of stochastic neurons is described. ...
Training involved 500 sweeps through the 700 examples. For testing, each net was run 10 times to estimate the expected description length of the image. ...
A neural net with 16 input units, 8 units in the first hidden layer, and 1 hidden unit in the second hidden layer was trained on produced by the generative model. ...
doi:10.1126/science.7761831
pmid:7761831
fatcat:ul2go6tkb5b2vdtgawfhddrd2u
Learning to simulate precipitation with supervised and generative adversarial modelling
[article]
2022
figshare.com
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This might change with more careful training (hyperparameter tuning). • The main difference between the supervised and generative models lies in the stochastic nature of the predictions as shown in Fig ...
The decoder path combines the feature and spatial information through up-convolutions and concatenations with high-resolution features from the encoder. • The V-NET is aimed at modelling volumetric data ...
doi:10.6084/m9.figshare.19779964.v1
fatcat:rv65m5gchfaejhsl7rppc3dkzy
SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Based on this perspective, we propose a neural stochastic differential equation model (SDE-Net) which consists of (1) a drift net that controls the system to fit the predictive function; and (2) a diffusion ...
The Bayesian framework provides a principled way of uncertainty estimation but is often not scalable to modern deep neural nets (DNNs) that have a large number of parameters. ...
We propose a deep neural net model for uncertainty quantification based on neural stochastic differential equation. ...
arXiv:2008.10546v1
fatcat:2tffhdk3ovaoxf4ybbx42pjykq
Learning to simulate precipitation with supervised and generative learning models
2020
Zenodo
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This might change with more careful training (hyperparameter tuning). • The main difference between the supervised and generative models lies in the stochastic nature of the predictions as shown in Fig ...
The decoder path combines the feature and spatial information through up-convolutions and concatenations with high-resolution features from the encoder. • The V-NET is aimed at modelling volumetric data ...
doi:10.5281/zenodo.4106514
fatcat:etshystsgjasnaaxkhdzycpnby
« Previous
Showing results 1 — 15 out of 25,697 results