Questions tagged [noise]
The noise tag has no usage guidance.
0
votes
1answer
47 views
what is correct way to perform normalization on data in Auto encoder?
working on anomaly detection problem. i'm using auto-encoder to denoise given input. I trained network with normal data(anomaly free). so model predict normal state of given input. Normalization of ...
3
votes
0answers
31 views
Training deep CNN with noisy dataset
I am training a Mask RCNN model with a train dataset that has been generated from some simple computer vision operations (color thresholding) and some morphological filtering.
The train set captures ...
1
vote
1answer
45 views
Effect of adding gaussian noise to the input layer in a CNN
I often come across Keras code that adds GaussianNoise to the input, however its not clear to me what advantages does it offer to the learning.
...
0
votes
0answers
4 views
A noise robust Local binary patterns variant
I’m thinking of using Local Binary Patterns (LBP) to extract features from MRI images of brain tumours to build a module for classification, due to its computational simplicity and good performance, ...
0
votes
0answers
42 views
How to create a complex Gaussian random noise with a specific covariance matrix
I am trying to generate a complex Gaussian white noise, with zero mean and the covariance matrix of them is going to be a specific matrix which is assumed to be given.
Assume i to be a point on the ...
0
votes
1answer
28 views
How can I avoid requiring global information for performing regression on meter variables?
Note: With a meter variable a timestamped value is the sum of all previous differences plus a difference to the most recent value. Think of a electricity meter counting the use of energy.
The goal ...
2
votes
1answer
48 views
Paramaeter estimation in noisy conditions with Machine Learning, possible?
Let's take two constants, $\alpha$ and $\beta$, both are given by two functions $f_1(\vec{\theta})$ and $f_2(\vec\theta$) (the model). These functions are known: we have an analytical closed ...
1
vote
0answers
39 views
Rain radar image noise reduction and cleanup
An application that I am building is plotting rain radar images on map. The images are transparent PNGs that are sourced straight from the local meteorological service.
As can be seen in the example, ...
2
votes
0answers
193 views
Training on accurate data versus noisy data
I have data currently available that is very accurate and I would like to train my classification methods on this set of clean data to learn the important markers for distinguishing between classes. ...
0
votes
1answer
18 views
Reducing noisy data from non normal distribution of data with std deviation?
I have used MATLAB code and get the two different row vectors A=1×18 and B=1×350. From both row vectors separately I need to remove the noisy data by using standard deviation. But the problem is that ...
3
votes
2answers
62 views
What is the loss function defined by Mnih and Hinton in their paper “Learning to Label Aerial Images from Noisy Data”?
In section 3.3 of the paper, they state that they use the cross entropy.
Then they define the probability for a label to be a false positive as $\theta_0$ and a false negative as $\theta_1$.
They use ...
1
vote
1answer
19 views
When we should use binning to redure noise? or How we find out we have noise?
I read several times which binning is helpful for reducing the noise of data. But how can we find out our data has noise? What if our data is clean and we reduce the accuracy of data?
Is there any ...
1
vote
0answers
38 views
Rprop is too noisy
Is there a way to reduce the noisiness and stochasticity of Rprop (and for that matter the iRprop+)?
Specifically, in deep networks (with 8+ layers) this effect starts to become apparent, as the ...
6
votes
2answers
2k views
Can Neural Networks be trained to smooth values / output the average?
Let's say we have a neural network with one input neuron and one output neuron. The training data $(x, f(x))$ is generated by a process
$$f(x) = ax + \mathcal{N}(b, c)$$
with $a, b, c \in \mathbb{R}^...
