Novel approaches to confidence bound generation for neural network representations

1997 ◽  
Author(s):  
R. Shao
Keyword(s):  
Neural Network ◽  
Confidence Bound ◽  
Novel Approaches

scholarly journals Multi-Feedback Bandit Learning with Probabilistic Contexts

2020 ◽  
Author(s):  
Luting Yang ◽  
Jianyi Yang ◽  
Shaolei Ren
Keyword(s):  
Neural Network ◽  
Reproducing Kernel ◽  
Learning Algorithm ◽  
Side Information ◽  
Reproducing Kernel Hilbert Space ◽  
Confidence Bound ◽  
Standard Assumption ◽  
Reward Function ◽  
Machine Learning Model ◽  
Upper Confidence Bound

Contextual bandit is a classic multi-armed bandit setting, where side information (i.e., context) is available before arm selection. A standard assumption is that exact contexts are perfectly known prior to arm selection and only single feedback is returned. In this work, we focus on multi-feedback bandit learning with probabilistic contexts, where a bundle of contexts are revealed to the agent along with their corresponding probabilities at the beginning of each round. This models such scenarios as where contexts are drawn from the probability output of a neural network and the reward function is jointly determined by multiple feedback signals. We propose a kernelized learning algorithm based on upper confidence bound to choose the optimal arm in reproducing kernel Hilbert space for each context bundle. Moreover, we theoretically establish an upper bound on the cumulative regret with respect to an oracle that knows the optimal arm given probabilistic contexts, and show that the bound grows sublinearly with time. Our simula- tion on machine learning model recommendation further validates the sub-linearity of our cumulative regret and demonstrates that our algorithm outper- forms the approach that selects arms based on the most probable context.

scholarly journals Tensor-Based Algorithms for Image Classification

Algorithms ◽  
2019 ◽  
Vol 12 (11) ◽  
pp. 240 ◽  
Author(s):  
Stefan Klus ◽  
Patrick Gelß
Keyword(s):  
Neural Network ◽  
Image Classification ◽  
State Of The Art ◽  
The Other ◽  
Learning Problems ◽  
Governing Equations ◽  
Data Set ◽  
Tensor Networks ◽  
Multidimensional Approximation ◽  
Novel Approaches

Interest in machine learning with tensor networks has been growing rapidly in recent years. We show that tensor-based methods developed for learning the governing equations of dynamical systems from data can, in the same way, be used for supervised learning problems and propose two novel approaches for image classification. One is a kernel-based reformulation of the previously introduced multidimensional approximation of nonlinear dynamics (MANDy), the other an alternating ridge regression in the tensor train format. We apply both methods to the MNIST and fashion MNIST data set and show that the approaches are competitive with state-of-the-art neural network-based classifiers.

scholarly journals Neural Network Based Non-parametric Confidence Bound Estimation for MSPC Chart

2004 ◽  
Vol 40 (6) ◽  
pp. 599-604
Author(s):  
Xiongfeng FENG ◽  
Masanori SUGISAKA ◽  
Xianhui YANG ◽  
Yongmao XU
Keyword(s):  
Neural Network ◽  
Confidence Bound ◽  
Bound Estimation ◽  
Non Parametric

scholarly journals Brain Tumor Detection: 2 Novel Approaches

2020 ◽  
Author(s):  
Donghyun Kim
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Brain Tumor ◽  
Complexity Theory ◽  
Granular Computing ◽  
Circuit Complexity ◽  
Ensemble Methods ◽  
Tumor Detection ◽  
Classification Algorithms ◽  
Novel Approaches

In this paper, we propose 2 novel methods for brain tumor detection in MRI images. In the first proposed approach, we build upon prior research on ensemble methods by testing the concatenation of pre-trained models: features extracted via transfer learning are merged and segmented by classification algorithms or a stacked ensemble of those algorithms. In the second approach, we expand upon prior studies on convolutional neural networks: a convolutional neural network involving a specific module of layers is used for classification. The first approach achieved accuracy scores of 0.98 and the second approach achieved a score of 0.863, outperforming a benchmark VGG-16 model. Considerations to granular computing and circuit complexity theory are given in the paper as well.

Novel Approaches to Low-Voltage Scanning Electron Microscopy

1990 ◽  
Vol 48 (1) ◽  
pp. 366-367
Author(s):  
Arthur V. Jones
Keyword(s):  
Electron Microscopy ◽  
Scanning Electron Microscopy ◽  
Low Voltage ◽  
Electron Optics ◽  
Current Interest ◽  
New Concepts ◽  
Opportune Time ◽  
Novel Approaches ◽  
Voltage Scanning ◽  
Scanning Electron

In comparison with the developers of other forms of instrumentation, scanning electron microscope manufacturers are among the most conservative of people. New concepts usually must wait many years before being exploited commercially. The field emission gun, developed by Albert Crewe and his coworkers in 1968 is only now becoming widely available in commercial instruments, while the innovative lens designs of Mulvey are still waiting to be commercially exploited. The associated electronics is still in general based on operating procedures which have changed little since the original microscopes of Oatley and his co-workers.The current interest in low-voltage scanning electron microscopy will, if sub-nanometer resolution is to be obtained in a useable instrument, lead to fundamental changes in the design of the electron optics. Perhaps this is an opportune time to consider other fundamental changes in scanning electron microscopy instrumentation.

Autofluorescence spectroscopy of oral leukoplakia using an artificial neural network

2000 ◽  
Vol 25 (4) ◽  
pp. 325-325
Author(s):  
J.L.N. Roodenburg ◽  
H.J. Van Staveren ◽  
N.L.P. Van Veen ◽  
O.C. Speelman ◽  
J.M. Nauta ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Oral Leukoplakia ◽  
Autofluorescence Spectroscopy ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document