Scribd
Upload
9 views15 pages

DL Lect 7

Uploaded by

knada1786
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
9 views15 pages

DL Lect 7

Uploaded by

knada1786
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 15

Deep Learning for Computer Vision

Dr. Basma M. Hassan


Faculty of Artificial Intelligence
Kafrelsheikh University

2024/2025
Deep Learning for Computer Vision

Lecture 7:
Outlines

• Batch Normalization
• Batch Normalization Algorithm
• Underfitting and Overfitting
• Avoiding Overfitting
➢ Cleaning Dataset
➢ Dropout Regularization
➢ Dataset Augmentation
➢ Regularization
➢ Other regularization techniques
Batch Normalization
• Although using ELU(or any variant Of ReLlJ) can remarkably reduce the vanishing/exploding gradients
problems at the beginning of training, the use of ELU cannot guarantee that vanishing/exploding
gradients won't come back during training.
• To address this issue, Batch Normalization (BN) can be implemented.
• BN consists Of adding an operation to the model just before or after the activation function Of each
hidden layer.
• We will simply employ zero-centering and normalizing each input.
• This operation allows the model to learn the optimal scale and the mean of each layer's inputs.
• To employ zero-center and normalize the inputs, we will need to estimate each input's mean ( )
• and standard deviation ( ) over the current mini-batch.
Batch Normalization Algorithm
Underfitting and Overfitting

❑ Essential problem of DL is to how to make and algorithm performs


well on training data as well as new data (unseen before).
❑ One of the most common problems faced is overfitting.
❑ DNNs typically have millions or tens of thousands of parameters.
❑ Too many parameters give the DNN s an incredible amount of
freedom to fit variety of complex datasets.
❑ Although, there is a great flexibility to fit. the DNN can be prone to
overfitting the training set.
❑ With overfitting, the model performs exceptionally well with training
data, but not as well with testing data.
Good Fitting, Underfitting, and Overfitting

❑ Underfitting: The trained model does not fit the dataset well or in other words the trained model
underestimate the dataset
❑ Overfitting: The trained model fits the dataset exceptionally well. but not the unseen data
❑ Good fitting: The trained model fits the dataset relatively well as well as the unseen data
• Underfitting: The trained model does not fit the dataset well
Good Fitting, or in other words the trained model underestimate the
dataset
Underfitting, and • Overfitting: The trained model fits the dataset exceptionally
well. but not the unseen data
Overfitting • Good fitting: The trained model fits the dataset relatively well
as well as the unseen data
Avoiding The challenge of overfitting can be
addressed through
Overfitting • Early Stopping.
Through • Cleaning data.

Regularization • Dropout.
Avoiding Cleaning Dataset
• Reduce number of features:
Overfitting • Manually select which features to keep
Avoiding Overfitting

Dropout Regularization
• Dropout Removes randomly some
neurons every iteration of training
• These models normally perform better
and memorize less data
Dataset Augmentation
➢ More data means better model.
➢ Data can be augmented by
creating fake data and adding
them to the dataset.
➢ This can be done by applying
transformation on the existing
dataset to get synthesized data.
• Regularization is used for tweaking the loss function
through adding an additional penalty term in the error
function.
• The additional term enables to control the excessively
fluctuating function such that the coefficients that take
extreme values.
• This way we help the network to have small weights.
Regularization • Large weights in ANN normally give an indication of a more
complex network that has overfitting.
• L1 and L2 vector norm penalty can be added to the
optimization of the NN and produce smaller weights.
• L1 and L2 regularization to constrain the NN's connecting
weights (but typically not the biases).
L1: Sum of the absolute weights.
L2: Sum of the squared weights.
LIL2: Sup of the absolute and the squared weights.
Regularization
• If you want to apply Ci regularization, replace
keras.regularizers.l2() by

• If you want to apply both l1 and l2 regularization, replace


keras.regularizers.l2() by

Regularization By default, no regularizer is used in any layers.

You might also like