Scribd
Upload
5 views

Data Science

AI class 10

Uploaded by

panu.sahasra
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
5 views

Data Science

AI class 10

Uploaded by

panu.sahasra
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 29

ARTIFICIAL INTELLIGENCE

– DATA SCIENCE
AI Need Data

 Artificial Intelligence is a technology which completely depends on data


 It is the data which is fed into the machine which makes it Intelligent
 Data is the foundation of Artificial Intelligence which is available around us.
 AI consumes data in order to learn. Hence AI doesn’t work without data.
 Depending on type of data given to an AI System, classified into three important Domains
namely:

 Data Science
 Computer Vision
 Natural Language Processing
What is Data Science ?

 It is the domain of computer science where we extract insights from available data with the help
of scientific methods, Algorithms and Statistics.
 Data Science is a technology that does analysis of data to create impactful solution from given
data or predict outcomes for problem statement.
 Data Science is used to solve real life problems using Data.
Internet Search Digital Advertisements

Applications of Data Science


Applications of Data Science

Website Image Recognition


Recommendations

Speech Recognition Airline route


Planning

Fraud & Risk Detection Medicine

Gaming Virtual Reality


Revisiting AI Project Cycle
Scenario

In Most of Cases we find Food is Wasted at End of Day


which is Unusable. We find this mostly in restaurants,
marriages ….
Food Wastage – Data @ Restaurants
Problem Scoping
As we know about the scenario, let us take a deeper look into the problem
to find out more about various factors around it

Lets explore the 4Ws Problem Canvas around the situation:

Who • Who is having the problem ?


Canvas
What • What is the nature of their problem ?
Canvas
Where • Where does the problem arise ?
Canvas
• Why do we think it is a problem worth
Why solving ?
Who Canvas – Who is Having the
Problem?

Who are Stake • Restaurants offering buffets


• Restaurant Chefs
Holders

What do we • Restaurants cook food in bulk every day for their


buffets to meet their customer needs.
know about • They estimate number of customers that would

them walk into their restaurant every day.


What Canvas – What is the Nature of their
Problem?
• Quite a large amount of food is leftover everyday
What is the unconsumed at the restaurant which is either thrown
away or given for free to needy people
problem ? • Restaurants have to bear everyday losses for the
unconsumed data

How do you • Restaurant Surveys have shown that restaurants face


know it is a this problem of food waste.
problem ?
Where Canvas – Where does the Problem
Arise ?

What is the context / • Restaurants which serve buffet


situation in which the food
stake holders
experience this
• At end of day when no further
problem? food consumption is possible
Why – Why do you think it is a problem worth
solving?
• If the restaurant has a proper estimate
What would be of of the quantity of food to be prepared
key value to the everyday the food waste can be
stakeholders reduced.

• Less or no food would be left


How would it unconsumed
improve their • Losses due to unconsumed food would
situation reduce considerably.
PYTHON FOR DATA SCIENCE
 Data Science is using a combination of Python and Mathematical concepts like Statistics, Data
Analysis, Probability, etc….
 A File created in python and saved with an extension .py is called a module. A collection of
relevant modules saved under the same directory and a name is called a package. Some of
the open –source packages available needed for Artificial Intelligence are:

 NumPy: Numerical Array Data Handling package. It is used for data analysis and calculation
related to large numerical data sets.

 OpenCV: Image Processing Package. It is used for manipulating and processing of images like
cropping, resizing, editing etc…

 Matplotlib: Data Visualisation package. It is used for the graphical representation to produce
high quality data visualization of the numerical data.

 NLTK(Natural Language Tool Kit): Natural Language processing package. It helps in tasks
related to textual data.

 Pandas: Data related to 2 or more dimensions is handled using pandas. The source of data is
data arranged in tabular form either using spreadsheets or database software.
Understanding K- Nearest Neighbour Model
(K-NN)
 K-Nearest Neighbour Model is a supervised machine learning algorithm based on supervised learning
technique.
 It is actually used to solve both classification and regression problems to estimate the possibility of a
new data to become a member of specific data group that is much similar to new data.
 The K-NN algorithm assumes that similar things exists in close proximity. It blindly follows the saying
“Birds of same feather flock together”.
 It is also called as lazy learner algorithm because it doesn’t learn from the training set immediately
instead it stores the data set and at the time of classification, it performs the action on data cell.
K Nearest Neighbour (KNN) Algorithm : Illustration
Why We Need KNN
Advantages of KNN Algorithm
 It is simple to understand and implement
 It is versatile for regression and classification
 It gives high accuracy using simple supervised learning techniques
 It is more effective for large training data
 It is very useful for non linear data

Disadvantages of KNN Algorithm


 Accuracy of algorithm depends on quality of data
 The cost of predicting K Nearest neighbour is very high
 Not suitable for data with many features or parameters
 Occupies a lot of memory space as it stores a lot of training data needed for smooth functioning of
algorithm
Thank
You

You might also like