Scribd
Upload
2 views

Deep Learning_Lecture 1_Introduction

The lecture presented by Dr. Hanaa Bayomi covers the types of machine learning, including supervised and unsupervised learning, and emphasizes the importance of feature selection for improving model performance. It also contrasts machine learning with deep learning, highlighting differences in data and hardware dependency, execution time, and feature engineering. The document provides insights into how feature selection can enhance model accuracy and reduce complexity.

Uploaded by

hazemkotp14
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
2 views

Deep Learning_Lecture 1_Introduction

The lecture presented by Dr. Hanaa Bayomi covers the types of machine learning, including supervised and unsupervised learning, and emphasizes the importance of feature selection for improving model performance. It also contrasts machine learning with deep learning, highlighting differences in data and hardware dependency, execution time, and feature engineering. The document provides insights into how feature selection can enhance model accuracy and reduce complexity.

Uploaded by

hazemkotp14
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/ 37

Lecture 1

Deep Learning
Presented by : Dr.Hanaa Bayomi
h.mobarz@fci-cu.edu.eg
Machine Learning types
Machine Learning types
Learning Types
Supervised Unsupervised

Discrete
Classification Clustering
Continuous

Regression Dimensionality reduction


http://scikit-learn.org/stable/tutorial/machine_learning_map/index.html
Machine Learning types
Feature selection
Feature selection

Performance of Machine Learning model depend on


Choice of algorithm
Feature selection
Feature creation
Model selection

Top reasons to use feature selection are:


It enables the machine learning algorithm to train faster.
It reduces the complexity of a model and makes it easier to interpret.
It improves the accuracy of a model if the right subset is chosen.
It reduces overfitting.
Feature selection
Feature selection
Data Separability Nature
Machine Learning VS Deep Learning

1- Data Dependency
- Deep learning need large amount of data to understand it perfectly
Machine Learning VS Deep Learning

2- Hardware Dependency
- Deep learning algorithms heavily depend on high-end
machines This is because the requirements of deep learning
algorithm include GPUs which are an integral part of its working.
- Machine Learning which can work on low-end machines.

3- Execution time
- deep learning algorithm takes a long time to train. This is because
there are so many parameters in a deep learning algorithm that training
them takes longer than usual.
Machine Learning VS Deep Learning

4- Feature engineering
- Deep learning algorithms try to learn high-level features from data.
- Machine Learning which can work on low-end machines.

You might also like