What is Deep Learning | Deep Learning Simplified | Deep Learning Tutorial | Edureka

Copyright © 2017, edureka and/or its affiliates. All rights reserved.
Agenda
 What Is Artificial Intelligence ?
 What Is Machine Learning ?
 Limitations Of Machine Learning
 Deep Learning To The Rescue
 What Is Deep Learning ?
 Deep Learning Applications

Agenda
 What Is Artificial Intelligence?
 What Is Machine Learning?
 Limitations Of Machine Learning?
 Deep Learning To The Rescue
 What Is Deep Learning?
 Deep Learning Applications

Why Artificial Intelligence?
Why we need Artificial Intelligence?

Let’s understand this with an example:
If a car exceeds the speed limit, then for a human to monitor and note down all the
numbers is not possible.

In order to solve it, we can use a machine to capture the
number plate picture and covert it into a text format
Convert the picture into text
UK PL8TE

What Is Artificial Intelligence?
Now, let’s understand what is Artificial Intelligence.

What Is Artificial Intelligence?
Artificial Intelligence is the capability of a machine to imitate intelligent human behavior.
AI is accomplished by studying how
human brain thinks, and how
humans learn, decide, and work
while trying to solve a problem
Outcomes of this study is used as a
basis of developing intelligent
software and systems.

Applications Of Artificial
Intelligence
Time to understand where can we use Artificial Intelligence.

Applications Of Artificial Intelligence
Speech
Recogniti
on
Understanding Natural LanguageSpeech Recognition Image Recognition

Subsets Of Artificial Intelligence
We’ll learn more about Deep Learning when we discuss Deep
networks and Neural networks in module 2 and 3
Artificial Intelligence
Machine Learning
Deep
Learning
Deep Learning is a subset of
Machine Learning
Machine Learning is a
subset of AI
Deep Learning uses
neural networks to
simulate human like
decision making

Machine Learning
Let’s understand what is Machine Learning.

Machine Learning
▪ Machine Learning is a type of artificial intelligence (AI) that provides computers with the ability to
learn without being explicitly programmed.
Problem Statement: Determine the specie of the flower
Learn from the dataset

Machine Learning
▪ Machine Learning is a type of artificial intelligence (AI) that provides computers with the ability to
learn without being explicitly programmed.
Problem Statement: Determine the specie of the flower
New Input
Sepal length, Sepal width, Petal
Length, Petal Width
Learn from the dataset
Predict the specie of the flower

Types Of Machine Learning
Let’s look at various different types of ML.

Types Of Machine Learning – Supervised Learning
Supervised Learning is where you have input variables (x) and an output variable (Y) and you use an
algorithm to learn the mapping function from the input to the output.

Types Of Machine Learning – Unsupervised Learning
Data
Class - 1 Class - 2
 High intra-class similarity
 Low inter-class similarity
 Unsupervised Learning is the training of a model using information
that is neither classified nor labelled.
 This model can be used to cluster the input data in classes on the
basis of their statistical properties.

Types Of Machine Learning – Reinforcement Learning
Agent
Environment
Action at
R t+1
S t+1
Reward
R t
State St
 Reinforcement Learning (RL) is learning by interacting with a space or an environment.
 An RL agent learns from the consequences of its actions, rather than from being taught explicitly. It
selects its actions on basis of its past experiences (exploitation) and also by new choices
(exploration).

Limitations Of Machine Learning
Let’s understand, even when Machine Learning is present why we need Deep Learning.

Cannot solve crucial AI problems like NLP, Image recognition
etc.
Are not useful while working with high dimensional data, that is
where we have large number of inputs and outputs
Machine
Learning

 One of the big challenges with traditional Machine Learning models is a process called feature
extraction.
 For complex problems such as object recognition or handwriting recognition, this is a huge
challenge.

Deep Learning To The Rescue
 Deep Learning models are capable to focus on the right features by themselves, requiring little
guidance from the programmer.
 These models also partially solve the dimensionality problem.
The idea behind Deep Learning is to build
learning algorithms that mimic brain.
What is
Deep
Learning?

Deep Learning To The Rescue
 Deep Learning is implemented through Neural Networks.
 Motivation behind Neural Networks is the biological Neuron.
X1
X2
Xn
Processing
Element
S = Xi Wi
Y
W1
W2
Wn
Y1
Y2
Yn
F(S
)
Summation
Transfer
Function
Outputs
Artificial Neural NetworkNeuron

What Is Deep Learning?
Input Layer
Hidden Layer 1
Hidden Layer 2
Output Layer
A collection of statistical machine learning techniques used to learn feature hierarchies often
based on artificial neural networks

Deep Learning – Use Case
Lets look at a use-case where we can use DL for image recognition.

Lets Understand This With An Example
Diagonal
Vertical
Solid
+ve weights
-ve weights

Deep Learning Example

Deep Learning Applications
Lets look at some applications of Deep Learning.

Deep Learning Applications
Self Driving Cars Voice Controlled Assistance
Automatic Image Caption Generation Automatic Machine Translation

Session In A Minute
Why Artificial Intelligence ? What is Artificial Intelligence? Subsets Of Artificial Intelligence
Machine Learning to Deep Learning What is Deep Learning? Deep Learning Applications

Applications Of Artificial Intelligence

What is Deep Learning | Deep Learning Simplified | Deep Learning Tutorial | Edureka

More Related Content

What's hot

Similar to What is Deep Learning | Deep Learning Simplified | Deep Learning Tutorial | Edureka

More from Edureka!

Recently uploaded

What is Deep Learning | Deep Learning Simplified | Deep Learning Tutorial | Edureka