1

# Data Augmentation: Gaussian Noise

Unsolved
###### Computer Vision

Difficulty: 3 | Problem written by zeyad_omar
##### Problem reported in interviews at

In deep learning, the learning process may turn to memorizing. This is known as overfitting, where the model gives high accuracy for the data in which the model was trained but gives terrible accuracy for the unseen data.

One of the techniques used to address this issue is the introduction of some random noise into the dataset to help the model become more generalized.

In this problem you are given an image and the mean and standard deviation of the noise and you are asked to return the image + noise.

*** Please use  np.random.seed(10) to match our test cases.

##### Sample Input:
<class 'list'>
x: [[1.31, 4.2, 3, 5], [1, 0, 1, 0], [1, 1, 1, 1]]
<class 'int'>
mean: 0
<class 'int'>
sigma: 1

##### Expected Output:
<class 'numpy.ndarray'>
[[ 2.6415865 4.91527897 1.45459971 4.99161615] [ 1.62133597 -0.72008556 1.26551159 0.10854853] [ 1.00429143 0.82539979 1.43302619 2.20303737]]

MLPro Premium also allows you to access all our high quality MCQs which are not available on the free tier.

Not able to solve a problem? MLPro premium brings you access to solutions for all problems available on MLPro

Have an issue, the MLPro support team is available 24X7 to Premium users.