Data Science – Deep Learning - Introduction
1. Deep learning – Introduction
Contents
1. Artificial intelligence vs Machine Learning vs Deep Learning........................................................... 2
1.1. Machine learning ......................................................................................................................... 2
1.2. Deep learning ............................................................................................................................... 3
1.3. Artificial intelligence .................................................................................................................... 3
2. Different models ................................................................................................................................ 4
3. Let’s understand Deep learning ......................................................................................................... 5
4. Differences between Deep Learning and Machine Learning ............................................................ 6
4.1. Data .............................................................................................................................................. 6
4.2. Computational Hardware CPU, GPU ............................................................................................ 6
4.3. CPU ............................................................................................................................................... 6
4.4. GPU .............................................................................................................................................. 7
5. Feature selection ................................................................................................................................ 8
6. Performance ....................................................................................................................................... 8
7. Neural networks ................................................................................................................................. 9
8. Types of neural networks................................................................................................................. 10
8.1. Deep learning applications ........................................................................................................ 10
1|Page 1.DEEP LEANRING-INTRO
Data Science – Deep Learning - Introduction
1. Deep learning – Introduction
1. Artificial intelligence vs Machine Learning vs Deep Learning
1.1. Machine learning
Machine learning is a part of artificial intelligence
Machine Learning is a technique to learn from the data and apply the
prediction on new data
Examples
Amazon using machine learning to give better product choice
recommendations to their costumers based on their preferences.
Netflix uses machine learning to give better suggestions to their users of
the TV series or movie or shows that they would like to watch & many
more
2|Page 1.DEEP LEANRING-INTRO
Data Science – Deep Learning - Introduction
1.2. Deep learning
Deep learning is a subset of machine learning.
The main difference between deep and machine learning is, machine
learning models works better but the model still needs some guidance.
If a machine learning model returns an inaccurate prediction then the
programmer needs to fix that problem explicitly.
In the case of deep learning, the model does it by itself.
Example
Automatic car driving system is a good example of deep learning.
1.3. Artificial intelligence
AI means the ability of computer program to function like a human
brain.
Machine learning and deep learning are the subsets of AI
The MOTO of AI is to replicate a human brain, the way a human brain
thinks, works and functions.
Currently AI is not yet fully implemented but we are very near to
establish that too.
Example
Sophia, the most advanced AI model present today.
3|Page 1.DEEP LEANRING-INTRO
Data Science – Deep Learning - Introduction
2. Different models
In ML we have worked with different models like linear regression,
logistic regression, KNN, Decision Tree & etc
4|Page 1.DEEP LEANRING-INTRO
Data Science – Deep Learning - Introduction
3. Let’s understand Deep learning
Deep learning is a subset of machine learning mainly using in Artificial
Neural Networks, which are inspired by the human brain.
Deep learning is able to capture required features automatically and
solving the problems.
DL is the technique that comes closest to the way humans learn.
Deep learning methods use neural network architecture.
That is why deep learning is often referred to as "deep neural networks”
5|Page 1.DEEP LEANRING-INTRO
Data Science – Deep Learning - Introduction
4. Differences between Deep Learning and Machine Learning
4.1. Data
Deep learning models works with very huge data
The more data you give to neural network, it will show much greater
accuracy than other machine learning models.
4.2. Computational Hardware CPU, GPU
ML models works with CPU[Central Processing Units]
DL models works with GPU[Graphical Processing Units] and TPS[Tensor
Processing Units]
o These are highly advanced processing systems
4.3. CPU
It is Central Processing Unit
It is a brain to the computer
Processing serial instructions
Good at speed during processing
Consumes more memory during processing
Companies like Intel, ARM and AMD produce the CPU and companies
6|Page 1.DEEP LEANRING-INTRO
Data Science – Deep Learning - Introduction
4.4. GPU
It is Graphical Processing Unit
Processing parallel instructions
Having very good speed compare to CPU
Consumes very less memory
Companies like Nvidia, AMD’s ATI produce the GPU
7|Page 1.DEEP LEANRING-INTRO
Data Science – Deep Learning - Introduction
5. Feature selection
In deep learning neural networks take care of the feature selection
automatically.
It decides a particular feature is important or not, and reduces the
corresponding weights to almost zero.
In machine learning algorithm, feature selection plays an important role
and we need to do keep focus on this
6. Performance
Deep learning gives very good performance compare to machine
learning
8|Page 1.DEEP LEANRING-INTRO
Data Science – Deep Learning - Introduction
7. Neural networks
Deep learning is implemented with the help of Neural Networks.
A neural network is a network or circuit of neurons to solve the problem.
The idea behind Neural Network is the biological neurons, which is
nothing but a brain cell.
Neural networks may have multiple hidden layers.
9|Page 1.DEEP LEANRING-INTRO
Data Science – Deep Learning - Introduction
8. Types of neural networks
There are mainly 3 types of neural networks in deep learning
o Artificial Neural Networks (ANN) or Feed-Forward Neural network
o Convolution Neural Networks (CNN)
o Recurrent Neural Networks (RNN)
8.1. Deep learning applications
Self Driving Cars
Fraud News Detection
Natural Language Processing
Virtual Assistants
Entertainment
Visual Recognition
Fraud Detection
Healthcare
Language Translations & etc
10 | P a g e 1.DEEP LEANRING-INTRO
