Artificial Intelligence Machine Learning Deep Learning PPT PowerPoint Presentation Slide Templates

Intelligence
Machine Learning
Deep Learning PPT
PowerPoint Presentation Slide Templates
Your Company Name

Table of Contents
2
Introduction
o What is AI?
o Introduction to AI Levels?
o Types of Artificial Intelligence
o AI VS machine learning vs deep learning
o Where is AI used?
o AI use cases
o Why is AI booming now?
o AI trend in 2020
Machine Learning
o What is Machine Learning?
o 7 Steps of Machine learning
o Machine Learning vs. Traditional Programming
o How does machine learning work?
o Machine learning Algorithms
o Machine learning use cases
o How to choose Machine Learning Algorithm
o Why to use decision tree algorithm learning
o Challenges and Limitations of Machine learning
o Application of Machine learning
o Why is machine learning important?
02
Deep Learning
o What is Deep Learning?
o Deep learning Process
o Classification of Neural Networks
o Types of Deep Learning Networks
o Feed-forward neural networks
o Recurrent neural networks (RNNs)
o Convolutional neural networks (CNN)
o Reinforcement Learning
o Examples of deep learning applications
o Why is Deep Learning Important?
o Limitations of deep learning
03
Difference between AI vs ML vs DL
o What is AI?
o What is ML?
o Machine Learning Process
o Deep Learning Process
o Difference between Machine Learning and Deep
Learning
o Which is better to start AI,ML or Deep learning
04
01

Table of Contents
3
Unsupervised Machine Learning
o What is Unsupervised Learning?
o How Unsupervised Machine Learning works
o Types of Unsupervised Learning
o Disadvantages of Unsupervised Learning
06
Reinforcement Learning
o What is reinforcement learning?
o How reinforcement learning works
o Types of reinforcement learning
o Advantage of reinforcement learning
o Disadvantage of reinforcement learning
07
Back Propagation Neural Network in AI
o Back Propagation Neural Network in AI
o What is Artificial Neural Networks?
o What is Backpropagation?
o Why We Need Backpropagation?
o What is a Feed Forward Network?
o Types of Backpropagation Networks
o Best practice Backpropagation08
Supervised Machine Learning
o Types of Machine Learning
o What is Supervised Machine Learning?
o How Supervised Learning Works
o Types of Supervised Machine Learning Algorithms
o Supervised vs. Unsupervised Machine learning
techniques
o Advantages of Supervised Learning
o Disadvantages of Supervised Learning
05
Expert System in Artificial Intelligence
o What is an Expert System?
o Examples of Expert Systems
o Characteristic of Expert System
o Components of the expert system
o Conventional System vs. Expert system
o Human expert vs. expert system
o Benefits of expert systems
o Limitations of the expert system
o Applications of expert systems
09

4
Introduction01
o What is AI?
o Introduction to AI Levels?
o Types of Artificial Intelligence
o AI VS machine learning vs deep learning
o Where is AI used?
o AI use cases
o Why is AI booming now?
o AI trend in 2020

Artificial intelligence (AI) is a popular branch of computer science that concerns with building
“intelligent” smart machines capable of performing intelligent tasks.
With rapid advancements in deep learning and machine learning, the tech industry is transforming
radically.
Artificial Intelligence
Transforming the Nature of Work, Learning, and Learning to Work
5
Machine Learning
Deep Learning
This slide is 100% editable. Adapt it to your needs and capture your audience's attention.

Introduction to AI Levels?
6
Artificial Narrow Intelligence
Artificial General Intelligence
Artificial Super Intelligence
Types of
Artificial
Intelligence

Types of Artificial Intelligence
7
Deep Learning Machine Learning Artificial Intelligence

8
Artificial intelligence (AI) is a popular
branch of computer science that concerns
with building “intelligent” smart machines
capable of performing intelligent tasks.
2018
2019
2020
2017 2016 2015
AI
2013 2014 2015 2016 2017
With rapid advancements in deep learning
and machine learning, tech industry is
transforming radically.
AI
Lorem IPSUM
Lorem Ipsum is simply dummy text of the
printing and typesetting industry. Lorem
Ipsum has been the industry's standard
dummy text ever since the 1500s
Lorem IPSUM
Lorem Ipsum is simply
dummy text of the
printing and typesetting
industry. Lorem Ipsum
has been the industry's
standard dummy text
ever since the 1500s
Lorem IPSUM
dummy text of the
standard dummy text
Lorem IPSUM
dummy text of the
standard dummy text
Lorem IPSUM
dummy text of the
standard dummy text
Lorem IPSUM
dummy text of the
standard dummy text
Lorem IPSUM
dummy text of the
standard dummy text
65%
35%

Machine Learning
9
Machine learning is a type of AI that enables machines to
learn from data and deliver predictive models.
The machine learning is not dependent on any explicit
programming but the data fed into it. It is a complicated
process.
Based on the data you feed into machine learning
algorithm and the training given to it, an output is
delivered.
A predictive algorithm will create a predictive model.
dummy text of the printing
and typesetting industry.
Lorem Ipsum has been the
industry's standard dummy
text ever since the 1500s
Lorem Ipsum is simply dummy
text of the printing and
typesetting industry. Lorem
Ipsum has been the industry's
standard dummy text ever
since the 1500s
Information

Deep Learning
10
Deep Learning is a subfield of machine learning that is
concerned with algorithms inspired by the brain's structure
A computer model can be taught using Deep Learning to
run classification actions using pictures, texts or sounds
as input
&
functions known as artificial neural
networks

AI VS Machine Learning VS Deep Learning
11
o Artificial Intelligence originated around
1950s
o AI represents simulate intelligence in
machines
o AI is a subset of data science
o Aim is to build machines which are
capable of thinking like humans
o Machine Learning originated around
1960s
o Machine learning is the practice of
getting machines to make decisions
without being programmed
o Machine learning is a subset of AI &
Data Science
o Aim is to make machines learn through
data so that they can solve problems
Artificial Intelligence Machine Learning Deep Learning
o Deep Learning originated around 1970s
o Deep Learning is the process of using
artificial neural networks to solve complex
problems
o Deep Learning is a subset of Machine
Learning, AI & Data Science
o Aim is to build neural networks that
au6tonetically discover patterns for
feature detection

Where is AI used?
12
Customer Experience
Supply Chain
Human Resources
Knowledge Creation
Research & Development
Fraud Detection
Real-time Operations Management
Customer Services
Risk Management & Analytics
Customer Insight
Pricing & Promotion
Predictive Analytics

AI Usecase in HealthCare
13
Research
Training Keeping Well
Early Detection
Diagnosis
Decision MakingTreatment
End of Life Care
AI and
Robotics

AI Use Cases in Human Resource
14
LEARNING
o Curated Training
o Skill Development
RECRUITING
o Dynamic Career Sites
o Smart Sourcing
ENGAGEMENT
o HR Chatbot
o Engagement Surveys
ONBOARDING
o Automated Messages
o Curated Videos
Employee Life Cycle

AI in Banking for Fraud Detection
15
Authorization System
Neural
Network Engine
Scoring Engine
Case Creation Module
Case
Management
Database
Expert Authorization
Response Module
Expert Rules Base
Configuration
Workstation
Expert Rules Execute
Rules Definition
Cardholder
Profiles
Postings
Payment System
Nonmonetary System
Analyst
Workstation
Auth Request1
3
Case Creation Rules Execute6
Payment and Non-Monetary Transactions8
Auth Recommendation4
Auth Request & Score2
Transaction & Score5
Case Information7

AI in Supply Chain
16
Structured & Unstructured
Information
Regulatory
Data
B2B Transaction
Data
Inventory
Data
Multimedia
Data
Sensor
Data
Logistics
Data
Trading
Partner
Data
Social
Media
Data
Procurement Manufacturing Customers ServiceLogistics
Pervasive Visibility
Proactive
Replenishment
Predictive Maintenance
Secure Device
Maintenance
Ecosystem
Integration
Unified
Messaging
Actionable
Insights
IIOT – Securely Provisionally People, System and Things
Secure Access Via Identity Management for Transient Users
Digital Ecosystem Data Lake

Ai Chatbots in Healthcare
17
Search Engine
Users learn to search
for information
Social Platforms
Like Facebook
connect users online
Smartphones
Bring the internet online
App Eco-system
Lets users download
and use apps easily
Messenger Apps
Lets users chat
anywhere, anytime
Self Learning machines
becomes smarter the
more they are used
Healthbots
Bring all of the above
together for
healthcare use cases

Why is AI booming now?
18
Global AI Revenue Forecast by 2025, Ranked by Use Case in millions US Dollar
8,097 7,540 7,336
4,680
4,201
3,714 3,655 3,564 3,169
0
2,000
4,000
6,000
8,000
Static Image Recognition,
Classification and Tagging
Algorithm Trading
Strategy Performance
Management
Efficient, Scalable
Processing of Patient Data
Predictive Maintenance Object Identification,
detection, classification,
tracking
Text Query of Images Automated Geophysical
Feature Detection
Content Distribution on
Social Media
Object detection &
classification, avoidance,
navigation
100% 92% 84%
45%54%
United
States
China India
GermanyIsrael
Penetration of Artificial Intelligence Skills, by Country
22%
24%
27%
36%
37%
51%
60%
60%
66%
71%
0 20 40 60 80 100
Fleet Mobile
Expediting Transactions
Production Floor Systems
Logistics & Supply Chain
Monitoring Through External Devices/Systems
Operational Environment
HR/Workforce Management
Security/Fraud
Customer Relation/Interaction (i.e., chatbots)
External Communication
Organizations deploying AI, by Functional Areas
This graph/chart is linked to excel, and changes automatically based on data. Just left click on it and select “Edit Data”.

10 AI Trend in 2020
19
Robotic Process Automation
AI will make Healthcare more Accurate
Data Modeling will move to the Edge
AI will Come for B2B
Ai-powered Chatbots
AI In Retail
Aerospace and Flight Operations
Controlled by AI
AI Mediated Media and Entertainment
Advanced Cybersecurity
Automated Business Process
AI Trends”
“2020

20
Machine Learning02
o What is Machine Learning?
o 7 Steps of Machine learning
o Machine Learning vs. Traditional Programming
o How does machine learning work?
o Machine learning Algorithms
o Machine learning use cases
o How to choose Machine Learning Algorithm
o Why to use decision tree algorithm learning
o Challenges and Limitations of Machine learning
o Application of Machine learning
o Why is machine learning important?

Machine Learning
21
Machine Learning is the result of General AI that involves developing machines
that can deliver results better than humans
Traditional
Programming
Data
(Input)
Program
Output
Data
(Input)
Output
Machine
Learning
Program
“Learning”
Machine
Learning SystemInput Data:
Feed Learner
Various Data
Output Data:
Present Rules

7 Steps of Machine Learning
22
Gathering Data
Preparing that Data Choosing a Model
Training Evaluation
Hyperparameter Tuning Prediction

Machine Learning vs. Traditional Programming
23
Traditional Modelling
Prediction
Result
Machine Learning
Learning
Model
Prediction
Result
Computer
New Data
Model
Sample Data
Expected
Result
Data
Handcrafted
Model
Computer
Computer

How does Machine Learning Work?
24
Identify, the problem to
be solved and create a
clear objective.
Define Objectives
Preparing data is a crucial
step and involves building
workflows to clean, match and
blend the data.
Prepare Data
Data is fed as input and the
algorithm configured with the
required parameters. A
percent of the data can be
utilized to train the model.
Train Model
Publish the prepared
experiment as a web
service, so applications can
use the model.
Integrate Model
Collect data from hospitals,
health insurance companies,
social service agencies, police
and fire dept.
Collect Data
Depend on the problem to be solved
and the type of data an appropriate
algorithm will be chosen.
Select Algorithm
The remaining data is utilized to test the
model, for accuracy. Depending on the
results, improvements, can be performed in
the “Train model’ and/or “Select Algorithm”
phases, iteratively.
Test Model

Machine Learning Algorithms
25
Machine Learning
o Linear
o Polynomial
o KNN
o Trees
o Logistic Regression
o Naïve-Bayes
o SVM
Regression
Decision Tree
Random Forest
Clustering
o SVD
o PCA
o K-means
o Apriori
o FP-Growth
Continuous
Categorical
Reinforcement
Classification
Association
Anlaysis
Hidden Markov
Model
Supervised Unsupervised

Machine Learning Use Cases
26
Energy Feedstock &
Utilities
o Power Usage Analytics
o Seismic Data
Processing
o Your Text Here
o Smart Grid
Management
o Energy Demand &
Supply Optimization
Financial
Services
o Risk Analytics &
Regulation
o Customer Segmentation
o Your Text Here
o Credit Worthiness
Evaluation
Travel &
Hospitality
o Aircraft Scheduling
o Dynamic Pricing
o Your Text Here
o Traffic Patterns &
Congestion
Management
Manufacturing
o Predictive
Maintenance or
Condition Monitoring
o Your Text Here
o Demand Forecasting
o Process Optimization
o Telematics
Retail
o Predictive Inventory
Planning
o Recommendation
Engines
o Your Text Here
o Customer ROI &
Lifetime Value
Healthcare &
Life Sciences
o Alerts & Diagnostics
from Real-time Patient
Data
o Your Text Here
o Predictive Health
Management
o Healthcare Provider
Sentiment Analysis

How to Choose Machine Learning Algorithm
27
How to Select Machine Learning Algorithms
What do you want to
do with your Data?
How to Select Machine Learning Algorithms
Algorithm Cheat Sheet
Additional
Requirements
Accuracy Linearity Number of
Parameters
Training
Time
Number of
Features

Why use Decision Tree Machine Learning Algorithm?
28
Decision Trees
To Classify
Decision Tree
Non-linear Relationship
between Predictors &
Response
Linear Relationship
between Predictors
& Response
Use c4.5
Implementation
Use Standard
Regression Tree
Responsible
Variable has only
2 Categories
Response Variable has
Multiple Categories
Use Standard
Classification here
Use c4.5
Implementation
To Predict
Responsible
variable is
Continuous

Challenges and Limitations of Machine learning
29
Advantages Disadvantages
Handling multi-dimensional & multi-
variety Data
Data
Acquisition
High error-
Susceptibility
Time and
Resources
Interpretation
Results
Easily Identifies Trends and Patterns
No Human Intervention needed
Continuous Improvement
Wide Applications

Application of Machine Learning
30
Automatic Language
Translation
Medical Diagnosis
Stock Market Trading
Online Fraud Detection
Virtual Personal Assistant
Email Spam and Malware FilteringSelf Driving Cars
Product Recommendations
Traffic Prediction
Speech Recognition
Image Recognition

Why is Machine Learning Important?
31
Phase 1 : Learning
Training
Data
o Normalization
o Dimension Reduction
o Image Processing, etc.
Pre-Processing
o Supervised
o Unsupervised
o Minimization, etc.
o Precision/recall
o Over fitting
o Test/cross Validation
data, etc.
Error Analysis
Model
New Data
Learning
Predicted DataPrediction
Phase 2: Prediction

32
Deep Learning
o Deep learning Process
o Classification of Neural Networks
o Types of Deep Learning Networks
o Feed-forward neural networks
o Recurrent neural networks (RNNs)
o Convolutional neural networks (CNN)
o Reinforcement Learning
o Examples of deep learning applications
o Why is Deep Learning Important?
o Limitations of deep learning
03

What is Deep Learning?
33
Deep Learning is a subfield of machine learning that is concerned with
algorithms inspired by the brain's structure and functions known as
artificial neural networks.
A computer model can be taught using Deep Learning to run
classification actions using pictures, texts or sounds as input.
Feature Extraction + ClassificationInput Output
Car
Not Car

Deep Learning Process
34
Understand
the Problem
Identify
Data
Select Deep
Learning
Algorithms
Training
the Model
Test the
Model

Classification of Neural Networks
35
x1
x2
xn
v11
v12
vpn
w11
w22
wmp ym
y2
y1
1
2
p
1
2
m
V1n
w1p
Input Layer Hidden Layer Output Layer

Types of Deep Learning Networks
36
Supervised
Artificial Neural Networks Used for Regression & Classification
Convolutional Neural Networks Used for Computer Vision
Recurrent Neutral Networks Used for Time Series Analysis
Unsupervised
Self-Organizing Maps Used for Feature Detection
Deep Boltzmann Machines Used for Recommendation Systems
AutoEncoders Used for Recommendation Systems
o Artificial Neural Networks (ANN)
o Convolutional Neural Networks (CNN)
o Recurrent Neural Networks (RNN)
o Self Organizing Maps (SOM)
o Boltzmann Machines (BM)
o AutoEncoders (AE)
Supervised Unsupervised
Deep Learning
Models

Feed-forward Neural Networks
37
Input Layer Hidden Layer Output Layer
Variable- #1
Variable- #2
Variable- #3
Variable- # 4
Output

Recurrent Neural Networks (RNNs)
38
x1
x2
y
Input Layer
Recurrent Network
Output Layer
Hidden Layers

Convolutional Neural Networks (CNN)
39
Take Car = A1 Truck = B1 VAN = C1 Bicycle = D1 Rest all be Same

40
uses rewards and punishment to train computing
models to perform a sequence of selections. Here
computing faces a game-like scenario where
it employs trial and error to answer. Based on the
action it performs, computing gets either rewards
or penalties. Its goal is to maximize the rewards.
Exploration Policy Neural Networks
Filters Memory
Algorithm
Agent Environment
Action
State, Reward

Examples of Deep Learning Applications
41
Image
Recognition
Portfolio
Management &
Prediction of Stock
Price Movements
Speech
Recognition
Natural Language
Processing
Drug Discovery &
Better Diagnostics of
Diseases in Healthcare
Robots and Self
- Driving Cars

Why is Deep Learning Important?
42
Deep Learning
Other Learning
Algorithms
Performance
Data

Limitations of Deep Learning
43
Limitations of
Deep Learning
Interpretability
Statistical ReasoningAmount of Data

44
Difference between AI vs ML vs DL04
o What is AI?
o What is ML?
o Machine Learning Process
o Deep Learning Process
o Difference between Machine Learning and Deep Learning
o Which is better to start AI,ML or Deep learning

Difference between AI vs ML vs DL
45This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Engineering of
making intelligent
machines and
programs
Artificial
Intelligence
Ability to learn without
being explicitly
programmed
Machine
Learning
Learning
based on deep
neural network
Deep
Learning

46
What is AI?
Artificial
Intelligence
(AI) is a popular branch of computer science that
concerns with building “intelligent” smart
machines capable of performing intelligent tasks.
With rapid advancements in deep learning and
machine learning, the tech industry is

What is ML?
47
Ordinary System With AI Machine Learning
Machine Learning
is a type of AI that enables machines to learn from data and deliver predictive models. The
machine learning is not dependent on any explicit programming but the data fed into it. It is a
complicated process. Based on the data you feed into machine learning algorithm and the training
given to it, an output is delivered. A predictive algorithm will create a predictive model.
Introduction to Machine learning
Learns
Predicts
Improves

48
Artificial intelligence (AI) is a popular branch of
computer science that concerns with building
“intelligent” smart machines capable of
performing intelligent tasks.
With rapid advancements in deep learning and
machine learning, the tech industry is

Modelling
Candidate & Final
Visualisation
Predictions & Strategy
Data
Raw & Training Data
Machine Learning Process
49
Data
Gathering
Data
Cleaning
Selecting
Right Algorithms
Building
Model & Finalising
Data Transformation
into Predictions

Deep Learning Process
50
Understand
the Problem
Identify
Data
Select Deep
Learning
Algorithm Training
the Model
Test
the Model

Difference between Machine Learning and Deep Learning
51
Machine Learning
Input Feature Extraction Classification Output
Car
Not Car
Deep Learning
Input OutputFeature Extraction + Classification
Car
Not Car

Which is better to start AI,ML or DL?
52
Any Technique which enables computers to mimic human
behavior.
Subset of ML which make the Computation of Multi-layer
Neural Networks Feasible.
Deep Learning
Subset of AI Techniques which use Statistical Methods to
Enable Machines to Improve with Experiences.
Machine Learning

53
Supervised Machine Learning05
o Types of Machine Learning
o What is Supervised Machine Learning?
o How Supervised Learning Works
o Types of Supervised Machine Learning Algorithms
o Supervised vs. Unsupervised Machine learning techniques
o Advantages of Supervised Learning:
o Disadvantages of Supervised Learning

Types of Machine Learning
Supervised
Learning
Unsupervised
Learning
Reinforcement
Learning
Inputs Outputs
Rewards
Inputs OutputsInputs Outputs
Training
Makes Machine Learn Explicitly
Data with Clearly defined Output is
given
Direct feedback is given
Predicts outcome/future
Resolves Classification and
Regression Problems
Machine Understands the data
(Identifies Patterns/ Structures)
Evaluation is Qualitative or Indirect
Does not Predict/Find anything
Specific
An approach to AI
Reward Based Learning
Learning form +ve & +ve
Reinforcement
Machine Learns how to act in a
Certain Environment
To Maximize Rewards

What is Supervised Machine Learning?
55
Input Raw Data
Processing
Output
Algorithm
Training
Data set
Desired
Output
Supervised Learning
Supervisor

How Supervised Machine Learning works
56
Step 1
Provide the Machine Learning Algorithm Categorized or
“labeled” Input and Output Data from to Learn
Step 2
Feed the Machine New, Unlabeled Information to
See if it Tags New Data Appropriately. If not, Continue
Refining the Algorithm
Machine Machine
Group 1
Group 2
Types of Problems to which it’s Suited
Classification
Sorting Items into Categories
Regression
Identifying Real Values
(Dollars, Weight, etc.)
Label
“Group 1”

Types of Supervised Machine Learning Algorithms
57
Classification
o Fraud Detection
o Email Spam Detection
o Diagnostics
o Image Classification
Regression
o Risk Assessment
o Score Prediction
Supervised
Learning

Supervised vs. Unsupervised Machine Learning Techniques
Supervised
Learning
o Classification
o Regression
Input & Output Data
Unsupervised
Learning
o Clustering
o Association
Input Data
Predictions &
Predictive Models
Patterns / Structure
Discovery

Advantages of Supervised Learning
59
It allows you to be very specific about the definition of the labels. In other words, you'll train
the algorithm to differentiate different classes where you'll set a perfect decision boundary.
You are ready to determine the amount of classes you would like to possess.
The input file is extremely documented and is labeled.
The results produced by the supervised method are more accurate and reliable as
compared to the results produced by the unsupervised techniques of machine learning. this
is often mainly because the input file within the supervised algorithm is documented and
labeled. this is often a key difference between supervised and unsupervised learning.
The answers within the analysis and therefore the output of your algorithm are likely to be
known thanks to that each one the classes used are known.
Advantages

Disadvantages of Supervised Learning
60
o Supervised learning are often a
posh method as compared with
the unsupervised method. The
key reason is that you
simply need
to understand alright and label the
inputs in supervised learning.
o It doesn’t happen in real time while the
unsupervised learning is about the
important time. this is often also a
serious difference between supervised
and unsupervised learning. Supervised
machine learning uses of-line analysis.
o It is needed tons of computation
time for training.
o If you've got a dynamic big and
growing data, you're unsure of the
labels to predefine the principles.
this will be a true challenge.

61
Unsupervised Machine Learning
o What is Unsupervised Learning?
o How Unsupervised Machine Learning works
o Types of Unsupervised Learning
o Disadvantages of Unsupervised Learning
06

What is Unsupervised Learning?
62
Unsupervised Learning
Input Raw Data OutputAlgorithm
Interpretation Processing
o Unknown output
o No Training Data Set

How Unsupervised Machine Learning works
63
Step 1
Provide the machine learning algorithm uncategorized,
unlabeled input data to see what patterns it finds
Step 2
Observe and learn from the patterns the
machine identifies
Machine Machine
Similar Group 1
Similar Group 2
Types of Problems to Which it’s Suited
Clustering
Identifying similarities in groups
For Example: Are there patterns in the data to
indicate certain patients will respond better to
this treatment than others?
Anomaly Detection
Identifying abnormalities in data
For Example: Is a hacker intruding in our
network?

Types of Unsupervised Learning
64
Dimensionality
Reduction
o Text Mining
o Face Recognition
o Big Data Visualization
o Image Recognition
Clustering
o Biology
o City Planning
o Targeted Marketing
Unsupervised
Learning

Disadvantages of Unsupervised Learning
65
You cannot get very specific about the definition of the
info sorting and therefore the output. This is
often because the info utilized in unsupervised learning is
labeled and not known. It's employment of the machine to
label and group the data before determining the hidden
patterns.
Less accuracy of the results. This is often also because
the input file isn't known and not labeled by
people beforehand , which suggests that the machine will got
to do that alone.
The results of the analysis can't be ascertained. there's no
prior knowledge within the unsupervised method of machine
learning. Additionally, the numbers of classes also are not
known. It results in the lack to determine the results
generated by the analysis.

66
Reinforcement learning07
o What is reinforcement learning?
o How reinforcement learning works
o Types of reinforcement learning
o Advantage of reinforcement learning
o Disadvantage of reinforcement learning

What is Reinforcement Learning?
67
Input Response Feedback Learns
It’s a
mango
Wrong!
It’s an
apple
Noted
It’s an
Apple
Reinforced
Response
Input

How Reinforcement Learning Works?
68
Input Raw Data Output
Reward
State
Selection of
Algorithm
Best Action
Environment
Agent

Types of Reinforcement Learning
69
Gaming
Finance Sector
Inventory Management
Manufacturing
Robot Navigation

Disadvantage of Reinforcement Learning
70
Less accuracy of the results. this is often also because the input file isn't known and not labeled by
people beforehand , which suggests that the machine will got to do that alone.
The results of the analysis can't be ascertained. There's no prior knowledge within the unsupervised
method of machine learning. Additionally, the numbers of classes also are not known. It results
in the lack to determine the results generated by the analysis Reinforcement learning as a
framework is wrong in many various ways, but it's precisely this quality that creates it useful.
You cannot get very specific about the definition of the info sorting and therefore the output. this is
often because the info utilized in unsupervised learning is labeled and not known. it's employment of
the machine to label and group the data before determining the hidden patterns.
Too much reinforcement learning can cause an overload of states which may diminish the results.
Reinforcement learning isn't preferable to use for solving simple problems.
Reinforcement learning needs tons of knowledge and tons of computation. it's data-
hungry. that's why it works rather well in video games because one can play the sport again and
again and again, so getting many data seems feasible.

71
Back Propagation Neural Network in AI08
o Back Propagation Neural Network in AI
o What is Artificial Neural Networks?
o What is Backpropagation?
o Why We Need Backpropagation?
o What is a Feed Forward Network?
o Types of Backpropagation Networks
o Best practice Backpropagation

Back Propagation Neural Network in AI
72
1 2
i1
i2 h2
w1
b1 b2
net out

What is Artificial Neural Networks?
73
Feed-Forward
Network Output
Input Layer
Network Inputs
Hidden Layer
Back Propagation
Output Layer

What is Backpropagation Neural Networking?
74
x
x
x
w
w
w
w
Difference in
Desired Values
Backprop Output Layer
Input Layer
1
1
Hidden Layer(s)
3
Output Layer
5
This slide is 100% editable. Adapt it to your needs and capture your audience's attention. s

Why We Need Backpropagation?
75
Backpropagation is fast, simple and
straightforward to program.
It has no parameters to tune aside
from the numbers of input.
It is a versatile method because it doesn't require prior
knowledge about the network.
It doesn't need any special mention
of the features of the function to
be learned.
It is a typical method that generally
works well.
Most prominent
advantages of
Backpropagation
Are:

What is a Feed Forward Network?
76
Input Layer
Hidden Layer
Output Layer

Types of Backpropagation Networks
77
It is one quite backpropagation network which
produces a mapping of a static input for static
output. it's useful to unravel static classification
issues like optical character recognition.
Static Back-propagation
Recurrent backpropagation is fed forward until a
hard and fast value is achieved. Then, the error is
computed and propagated backward.
Recurrent Backpropagation
The main difference between both of those methods is: that the mapping is rapid in static back-propagation
while it's nonstatic in recurrent backpropagation
o Static Back-propagation
o Recurrent Backpropagation

Best Practice Backpropagation
78
A neural network is a group of connected it I/O
units where each connection features
a weight related to its computer programs.
Backpropagation may be a short form for
"backward propagation of errors." it's a
typical method of coaching artificial neural
networks.
Backpropagation is fast, simple and
straightforward to program.
A feedforward neural network is a man-
made neural network.
BACKPROPAGATION

79
Expert System in Artificial Intelligence09
o What is an Expert System?
o Examples of Expert Systems
o Characteristic of Expert System
o Components of the expert system
o Conventional System vs. Expert system
o Human expert vs. expert system
o Benefits of expert systems
o Limitations of the expert system
o Applications of expert systems

Expert System in Artificial Intelligence
80
Knowledge
Base
Inference
Engine
User
Interface
User
(May not be an expert)
Knowledge
Engineer
Human
Expert
The Expert System in AI are computer
applications. Also, with the assistance of
this development, we will solve complex
problems. it's level of human intelligence
and expertise

Examples of Expert Systems
81
Expert System
User
Interface
Knowledge
Base
Inference
Engine
Non-expert
User
Knowledge from
an expert
Query
Advice
The Highest Level of Expertise
o The expert system offers the very best level of experience. It provides
efficiency, accuracy and imaginative problem-solving.
Right on Time Reaction
o An Expert System interacts during a very reasonable period of your time with the
user. the entire time must be but the time taken by an expert to urge the
foremost accurate solution for an equivalent problem.
Good Reliability
o The expert system must be reliable, and it must not make any an error.
Flexible
o It is significant that it remains flexible because it the is possessed by an
Expert system.
Effective Mechanism
o Expert System must have an efficient mechanism to administer the
compilation of the prevailing knowledge in it.
Capable of Handling Challenging Decision & Problems
o An expert system is capable of handling challenging decision problems and
delivering solutions.

Characteristic of Expert System
o The system must be capable of responding at A
level of competency adequate to or better than
an expert system within the field. the
standard of the recommendation given by the
system should be during a high level integrity
and that the performance ratio should be also
very high
o The system should be designed in
such how that it's ready to perform
within alittle amount of your time , like or
better than the time taken by a
person's expert to succeed in at a
choice point. An expert system that takes
a year to succeed in a choice compared
to a person's expert’s time of
1 hour wouldn't be useful
o Expert systems use symbolic
representations for knowledge
(rules, networks or frames) and
perform their inference through
symbolic computations that
closely resemble manipulations
of tongue
Use Symbolic
Representations
Adequate Response Time
High level Performance
This slide is 100% editable. Adapt it to your needs and capture your audience's attention. 82
o Expert systems are typically very domain specific. For ex.,
a diagnostic expert system for troubleshooting computers
must actually perform all the required data manipulation
as a person's expert would. The developer of such a
system must limit his or her scope of the system to
only what's needed to unravel the target problem. Special
tools or programming languages are often needed to
accomplish the precise objectives of the system
Domain Specificity
o The expert system must be as reliable as a
person's expert
Good Reliability
o The system should be understandable
i.e. be ready to explain the steps of
reasoning while executing. The expert
system should have an
evidence capability almost like the
reasoning ability of human experts
Understandable

Components of the Expert System
83
Explanation
Inference
Engine
Knowledge
Base
Acquisition
Facility
User
Interface
Experts and
Knowledge
Engineers
Users

Conventional System vs. Expert System
84
Knowledge domain break away the mechanism processing
The program could have made an error
Not necessarily need all the input/data
Changes within the rule are often made with ease
The system can work only with the rule as a tittle
Information and processing combined during a sequential file
The program isn't wrong
Need all the input file
Changes to the program are inconvenient
The system works if it's complete
01
02
03
04
05 05
04
03
02
01
vs

Human Expert vs. Expert System
85
Perishable
Difficult to Transfer
Difficult to Document
Expensive, especially top notch
Add Your Text Here
Permanent
Easy to Transfer
Easy to Document
Affordable, costly to develop, but cheap to operate
Add Your Text Here
Human Experts (Artificial ) Expert Systems

Benefits of Expert Systems
86
Fast Response
Easy to Develop and
Modify the System
Low Accessibility
Cost
Humans
Emotions are not
Affected
Error Rate are
Very Low
Data Warehousing

Limitations of the Expert System
87
Don’t Have Decision Making
Power Like Humans
Its Difficult to Maintain
Its Developed for a Specific Domain
Expert System is not Widely
used or Tested
Not Able to Explain the Logic
Behind the Decision
It cant Deal with the
Mixed Knowledge
Development Cost is High There are Chances of Errors

Knowledge domain (Finding out the faults in vehicles, computer)
Finance/Commerce (Stock market trading, airline
scheduling cargo scheduling)
Process Control System
Repairing
Monitoring system
Medical domain (Diagnosis
system, medical operations)
Warehousing
Optimization
ShippingDesign domain (Camera lens
design,automobile design)
Applications of Expert Systems
88

Artificial Intelligence Machine Learning Deep Learning PPT
PowerPoint Presentation slide templates Icons Slide
89

Bar Chart
91
0
10
20
30
40
50
60
70
80
90
100
Jan Feb Mar Apr May Jun
Sales(inUSDmillions)
Year 2020
100%
This graph/chart is linked to excel, and
changes automatically based on data. Just
left click on it and select “Edit Data”.
Product 01
Product 02
Product02
Product01

Stacked Column
92
Product 01
Product 02
4.3
2.5
-3.5
-4.5
2.4
4.4
-1.8
-0.8
-6
-4
-2
0
2
4
6
8
Sales(inUSDmillions)

Welcome to Our Agenda
93
This slide is 100% editable. Adapt it to your needs and
capture your audience's attention.
Agenda 01
Agenda 02
Agenda 03
Agenda 04
Agenda 05

Our Goal
94
This slide is 100% editable. Adapt it
to your needs and capture your
audience's attention.
Goal 3
This slide is 100% editable. Adapt it to
your needs and capture your
Goal 1
This slide is 100% editable. Adapt it
to your needs and capture your
Goal 2

Idea
Generation
95
This slide is 100% editable. Adapt
it to your needs and capture your
Text Here
Text Here
Text Here
Text Here

Venn
96
25%
75%
35%
Text Here
Text Here
Text Here

Timeline
97
20202016 2017 2018 2019
Text Here
Text Here
Text Here
Text Here
Text Here

Post It Notes
98
Text Here
Text Here
Text Here

Thank You
99
# street number, city, state
Address
0123456789
Contact Number
emailaddress123@gmail.com
Email Address

Artificial Intelligence Machine Learning Deep Learning PPT PowerPoint Presentation Slide Templates

More Related Content

What's hot (20)

Similar to Artificial Intelligence Machine Learning Deep Learning PPT PowerPoint Presentation Slide Templates (20)

More from SlideTeam (20)

Recently uploaded (20)

Artificial Intelligence Machine Learning Deep Learning PPT PowerPoint Presentation Slide Templates