Prerequisites for this

Course
Windows 10 Laptop with Good Internet
No basic knowledge is required.
What u will learn.
What is AI?.
● Intelligence demonstrated by the
Machines in contrast to Natural
Intelligence delivered by
Humans
“AI WILL BE THE BEST OR
WORST THING EVER
FOR HUMANITY.” – Elon Musk

● Intelligence is given by feeding

the experience of human to
machines in the form of data
Why AI?.
● “Success in creating AI would be the
AI automates repetitive learning and discovery
through data biggest event in human history.
● AI adds intelligence Unfortunately, it might also be the last,
● AI analyzes more and deeper data unless we learn how to avoid the
● AI achieves incredible accuracy
● 24x7
risks.” – Stephen Hawking
● Reduces Man power
How AI?.

See & Recognize: Computer Vision & Deep learning

Eye - Camera

Analyze & Learn: Machine Learning

Sensing organs - Sensors

Listen & Speak: Natural Language Processing

Ear & Mouth – Mic & Speaker
 ART
IFIC
IAL

Deep Learning in AI. INT

ELL
IGE
NCE

MACHI
NE
LEARN
ING

DEEP
LEARN
ING
Deep Learning.
Recognition
Brain
Vision

Training
Dataset Model Recognition
Why Deep Learning ?

Prediction

AI

Automatic Feature Extraction

Input Data It’s an apple
 Neuron & Activation Function. Cell Body
Neuron Dendrites Synapse
Axon
• Like a Human Brain, here a Neuron takes input and
do some function to give the output
• Function going to be the Mathematical function
• Those Function is known as ACTIVATION function

Activation Function

• Step Function
Neuron
• Sigmoid Function
• Tanh Function
• ReLU Function Inputs OUTPUT

Activation Fn.
 Deep Learning Libraries Keras
Tensor Flow Framework for Deep learning | Same
Numerical computation using data flow graphs | code for CPU & GPU | Uses
Backend for Keras | Distributed computing on Theano/TF as Backend | CNN | not
multiple GPU support multi GPU

Torch
Numerical Python & Old ML & DL library |
Supports CUDA - Compute
Scientific Python Unified Device Architecture
Basic operation such as Sorting, for parallel computation |
Reshaping, indexing | Scientific Supervised image problem
computing | Most new feature with CNN
belong in SciPy rather than
Numpy
Caffe
Caffe is a deep learning
framework made with expression,
Mxnet speed, and modularity in
mind.Very high performance |
Apache MXNet is an open-source deep learning software
Tuning Hyper parameters | CNN
framework, used to train, and deploy deep neural networks|
& RNN(Facebook extends) | |
More number of Language Bindings | Distributed computing
CPU & GPU
Applications of
AI
AI in Medical.
AI in Agriculture.
AI in Voice Assistance.
AI in Autonomous Vehicle.
AI in Search Engine.
AI in Social Media & Other.
Dialogflow.
Dialogflow is a natural language
understanding platform used to design and
integrate a conversational user interface into
mobile apps, web applications, devices, bots,
interactive voice response systems, and so
on.

● Small Talk
● Intents
● Entity
● Integration
● Pre built Agents
Applications of Chatbot.
 Voice Assistance
 Social Media
 Customer Support
 Helpdesk
 Medical Assistance
 Restaurant
 Transportation
 E-Commerce
Programming Languages for
AI. “In a way, AI is both closer and farther
● Python
● C++ off than we imagine. AI is closer to
● Matlab being able to do more powerful things
● Java
● LISP
than most people expect — driving
● Prolog cars, curing diseases, discovering
● Julia planets, understanding media. Those
● Haskell will each have a great impact on the
world, but we're still figuring out what
real intelligence is.” – Mark Zuckerberg
Python & Uses.
● Python is a popular programming language. It
was created by Guido van Rossum, and released
in 1991.
● Python is a programming language that lets you
work more quickly and integrate your systems
more effectively.

1. Web development
2. Handle Big data
3. Handles complex Mathematics
4. Software development
5. Connects to database systems
Installing Python
IDLE
PYTHON.ORG | MICROSOFT VISUAL STUDIO
Add two number.
a = 5.4
b = 4.6
sum = float(a) + float(b)
print(sum)

User Input.
a = input(“Enter number1: “)
b = input(“Enter number2: “)
sum = int(a) + int(b)
print(“The sum of {0} and {1} is {2}”.format(a, b,
sum))
If & Elif.
a = 33
b = 33
if a > b:
print(“a is greater than b")
elif a == b:
print("a and b are same")
else:
print("b is greater than a")

AND | OR.
a = 200
b = 33
c = 500
if a > b and c > a:
print("Both conditions are True")
#if a > b or c > a:
# print(“only one is True")
While.
i=1
while i < 20:
print(i)
i += 1

FOR.
for x in range(10):
print(x)

for x in range(1, 10):

print(x)

for x in range(1, 10, 2):

print(x)
Fuction.
def funName():
print("Hello from a function")

funName()

File Handling.
a = open(‘pantech.txt’, ‘r’)

print(a.read())

a.close()
What is Computer Vision?.
● Early experiments in computer vision took place in
the 1950s, using some of the first neural networks to
detect the edges of an object and to sort simple objects
into categories like circles and squares.

● Computer vision is an interdisciplinary scientific field

that deals with how computers can gain high-level
understanding from digital images or videos.
Image Processsing vs Computer vision.
Image processing, an image is "processed", transformations are
applied to an input image to get output image.

Computer vision, an image or a video is taken as input, and the

goal is to understand the image and its contents which uses image
processing algorithms to solve some of its tasks like human brain