This Artificial Intelligence presentation will help you understand what is Artificial Intelligence, types of Artificial Intelligence, ways of achieving Artificial Intelligence and applications of Artificial Intelligence. In the end, we will also implement a use case on TensorFlow in which we will predict whether a person has diabetes or not. Artificial Intelligence is a method of making a computer, a computer-controlled robot or a software think intelligently in a manner similar to the human mind. AI is accomplished by studying the patterns of the human brain and by analyzing the cognitive process. Artificial Intelligence is emerging as the next big thing in the technology field. Organizations are adopting AI and budgeting for certified professionals in the field, thus the demand for trained and certified professionals in AI is increasing. As this new field continues to grow, it will have an impact on everyday life and lead to considerable implications for many industries. Now, let us deep dive into the AI tutorial video and understand what is this Artificial Intelligence all about and how it can impact human life.
The topics covered in this Artificial Intelligence presentation are as follows:
1. What is Artificial intelligence?
2. Types of Artificial intelligence
3. Ways of achieving artificial intelligence
4. Applications of Artificial intelligence
5. Use case - Predicting if a person has diabetes or not
Simplilearn’s Artificial Intelligence course provides training in the skills required for a career in AI. You will master TensorFlow, Machine Learning and other AI concepts, plus the programming languages needed to design intelligent agents, deep learning algorithms & advanced artificial neural networks that use predictive analytics to solve real-time decision-making problems without explicit programming.
Why learn Artificial Intelligence?
The current and future demand for AI engineers is staggering. The New York Times reports a candidate shortage for certified AI Engineers, with fewer than 10,000 qualified people in the world to fill these jobs, which according to Paysa earn an average salary of $172,000 per year in the U.S. (or Rs.17 lakhs to Rs. 25 lakhs in India) for engineers with the required skills.
Those who complete the course will be able to:
1. Master the concepts of supervised and unsupervised learning
2. Gain practical mastery over principles, algorithms, and applications of machine learning through a hands-on approach which includes working on 28 projects and one capstone project.
3. Acquire thorough knowledge of the mathematical and heuristic aspects of machine learning.
4. Understand the concepts and operation of support vector machines, kernel SVM, Naive Bayes, decision tree classifier, random forest classifier, logistic regression, K-nearest neighbors, K-means clustering and more.
Comprehend the theoretic
Learn more at: https://www.simplilearn.com
2. What’s in it for you?
Ways of achieving artificial intelligence
Types of Artificial intelligence
Applications ofArtificial Intelligence
Use case - predicting if a person has diabetes or not
What is Artificial Intelligence?
content
3. Brief History of Artificial Intelligence
The word ‘Artificial
Intelligence’ coined by John
McCarthy
‘Shakey’ was the first general
purpose mobile robot built
Supercomputer ‘Deep blue’ was
designed which defeated the
world Chess champion in a game
First commercially successful
robotic vacuum cleaner
created
Speech recognition, RPA,
dancing robots, smart homes
and many more to come from
AI
1956 1969 1997 2002 2005-2018
What is Artificial Intelligence?
7. What is Artificial Intelligence?
Artificial Intelligence is a branch of Computer Science
dedicated to creating intelligent machines that work
and react like humans.
8. What is Artificial Intelligence?
Thanks! Any task you want
me to do for you?
12. Brief History of Artificial Intelligence
The word ‘Artificial
Intelligence’ coined by John
McCarthy
‘Shakey’ was the first general
purpose mobile robot built
Supercomputer ‘Deep blue’ was
designed which defeated the
world Chess champion in a game
First commercially successful
robotic vacuum cleaner
created
Speech recognition, RPA,
dancing robots, smart homes
and many more to come from
AI
1956 1969 1997 2002 2005-2018
Types of Artificial Intelligence
13. Types of Artificial Intelligence
Hi there! I have discovered four
different types of Ai. Come have a
look!
14. This kind of AI are purely reactive
and do not hold the ability to form
memories or use past experiences
to make decisions.These machines
are designed to do specific jobs
Types of Artificial Intelligence
Reactive machines
15. Types of Artificial Intelligence
Reactive machines
This kind of AI are purely reactive
and do not hold the ability to form
memories or use past experiences
to make decisions.These machines
are designed to do specific jobs
Limited memory
This kind of AI uses past
experience and the present data to
make a decision. Self driving cars
are a kind of limited memory AI
16. Theory of mind
These ai machines can
socialize and understand
human emotions. Machines
with such abilities are yet to
be built
Types of Artificial Intelligence
Reactive machines
This kind of AI are purely reactive
and do not hold the ability to form
memories or use past experiences
to make decisions.These machines
are designed to do specific jobs
Limited memory
This kind of AI uses past
experience and the present data to
make a decision. Self driving cars
are a kind of limited memory AI
17. Self awareness
this is the future ofAi.These
machines will be super
intelligent, sentient and
conscious
Theory of mind
Types of Artificial Intelligence
Reactive machines
This kind of AI are purely reactive
and do not hold the ability to form
memories or use past experiences
to make decisions.These machines
are designed to do specific jobs
Limited memory
These ai machines can
socialize and understand
human emotions. Machines
with such abilities are yet to
be built
This kind of AI uses past
experience and the present data to
make a decision. Self driving cars
are a kind of limited memory AI
18. Brief History of Artificial Intelligence
The word ‘Artificial
Intelligence’ coined by John
McCarthy
‘Shakey’ was the first general
purpose mobile robot built
Supercomputer ‘Deep blue’ was
designed which defeated the
world Chess champion in a game
First commercially successful
robotic vacuum cleaner
created
Speech recognition, RPA,
dancing robots, smart homes
and many more to come from
AI
1956 1969 1997 2002 2005-2018
Achieving Artificial Intelligence
19. Achieving Artificial Intelligence
Machine learning
Machine Learning provides Artificial Intelligence
with the ability to ‘Learn’.This is achieved by
using algorithms that discover patterns and
generate insights from the data they are exposed
to
20. Achieving Artificial Intelligence
Deep Learning
Deep learning provides artificial intelligence the
ability to mimic a human brain’s neural network. It
can make sense of patterns, noise and sources of
confusion in the data
Machine learning
Machine Learning provides Artificial Intelligence
with the ability to ‘Learn’.This is achieved by
using algorithms that discover patterns and
generate insights from the data they are exposed
to
25. Achieving Artificial Intelligence – Deep Learning
Labeled
photographs
landscapes portraits others
Segregated photos
Based on the features of each
photo, it segregates them
Bingo!
28. There are three main
layers in a neural
network
Achieving Artificial Intelligence – Deep Learning
29. The photos that we want to
segregate go into the input
layer
Input layer
Achieving Artificial Intelligence – Deep Learning
30. The hidden layers are responsible for all
the mathematical computations or
feature extraction on our inputs
Input layer
Hidden layers
Achieving Artificial Intelligence – Deep Learning
31. The accuracy of the predicted output
generally depends on the number of
hidden layers we have
Input layer
Hidden layers
Achieving Artificial Intelligence – Deep Learning
32. The output layer gives us the
segregated photos
Input layer
Hidden layers
Output layer
portrait
Landscape
Achieving Artificial Intelligence – Deep Learning
33. Let’s predict the airline
ticket prices using machine
learning
Achieving Artificial Intelligence – Machine Learning
34. These are the factors based on
which we are going to make the
predictions
Achieving Artificial Intelligence – Machine Learning
36. Here are some historical data of
ticket prices to train the machine
Old data
Achieving Artificial Intelligence – Machine Learning
37. Now that our machine is trained,
let’s give it new data for which it will
predict the prices
Old data
New data
Achieving Artificial Intelligence – Machine Learning
38. Old data
New data
The price is $1000!!
Achieving Artificial Intelligence – Machine Learning
39. Brief History of Artificial Intelligence
The word ‘Artificial
Intelligence’ coined by John
McCarthy
‘Shakey’ was the first general
purpose mobile robot built
Supercomputer ‘Deep blue’ was
designed which defeated the
world Chess champion in a game
First commercially successful
robotic vacuum cleaner
created
Speech recognition, RPA,
dancing robots, smart homes
and many more to come from
AI
1956 1969 1997 2002 2005-2018
Applications of Artificial Intelligence
49. Here, you have one
more application of
artificial intelligence
50. Brief History of Artificial Intelligence
The word ‘Artificial
Intelligence’ coined by John
McCarthy
‘Shakey’ was the first general
purpose mobile robot built
Supercomputer ‘Deep blue’ was
designed which defeated the
world Chess champion in a game
First commercially successful
robotic vacuum cleaner
created
Speech recognition, RPA,
dancing robots, smart homes
and many more to come from
AI
1956 1969 1997 2002 2005-2018
Use Case – Predict if a person has Diabetes
52. Use Case
The problem statement is to predict if a
person has diabetes or not!
Predict if a patient has diabetes based on previous
test data
Problem Statement
62. Use Case
#categorical features
assigned_group =
tf.feature_column.categorical_column_with_vocabulary_list
('Group',['A','B','C','D'])
#converting continuous to categorical
import matplotlib.pyplot as plt
%matplotlib inline
diabetes['Age'].hist(bins=20)
63. Use Case
age_buckets = tf.feature_column.bucketized_column(age,
boundaries=[20,30,40,50,60,70,80])
#combining all the features
feat_cols = [num_preg ,plasma_gluc,dias_press ,tricep
,insulin,bmi,diabetes_pedigree ,assigned_group, age_buckets]
#splitting the data
x_data = diabetes.drop('Class',axis=1)
labels = diabetes['Class’]
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test =
train_test_split(x_data,labels,test_size=0.33,
random_state=101)
64. Use Case
#applying input function
input_func =
tf.estimator.inputs.pandas_input_fn(x=X_train,y=y_train,ba
tch_size=10,num_epochs=1000,shuffle=True)
#creating the model
model =
tf.estimator.LinearClassifier(feature_columns=feat_cols,n_c
lasses=2)
model.train(input_fn=input_func,steps=1000)
65. Use Case
#prediction
pred_input_func = tf.estimator.inputs.pandas_input_fn(
x=X_test,
batch_size=10,
num_epochs=1,
shuffle=False)
predictions = model.predict(pred_input_func)
list(predictions)
66. Use Case
#evaluating the model
eval_input_func = tf.estimator.inputs.pandas_input_fn(
x=X_test,
y=y_test,
batch_size=10,
num_epochs=1,
shuffle=False)
results = model.evaluate(eval_input_func)
results
67. Use Case
So, we have managed to have
an accuracy of 71% and that’s
quite good for our model!
68. Use Case - Conclusion
So, we created a model that can predict
if a person has diabetes based on some
previous records of people who were
diagnosed with diabetes
69. Use Case - Conclusion
The model was implemented on python
using tensorflow