You are on page 1of 19

ARTIFICIAL INTELLIGENCE

III B. TECH I YEAR


ECE 2
AY: 2022-2023
Supervisor Name:
Revalla.Gnapika Dr.D.V.A.N.Ravikumar,
20JG1A0486 Associate Professor,
ECE Department.

DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING (ECE)

GAYATRI VIDYA PARISHAD COLLEGE OF ENGINEERING FOR WOMEN


MADHURAWADA, VISAKHAPATNAM-530048.
CONTENTS

 Artificial Intelligence
 Introduction to Python and use of Artificial
Intelligence in python.
 Use of Matplotlib in Python
 Use of Numpy in Python
 Use of Pandas in Python
 Machine Learning
 Project 1
 Project 2
 Project 3
About Internship Details
 Duration : 1st August to 15th November
 Domain : Artificial Intelligence.
 Artificial intelligence(AI) is to design a system capable of thinking for itself just like humans do..
 The aim of this Digit classification using CNN is to implement a classification algorithm to recognize
the handwritten digits.
 Fake news has been incurring many problems to our society. In this work ,i proposed a system to
detect fake news by using NLP .
 Human face detection has become a major field of interest in current project. Although we have
biometrics for this purpose but this face recognition system gives us high accuracy ,high enrolment
and verification rates.
ARTIFICIAL INTELLIGENCE :
ARTIFICIAL INTELLIGENCE (AI) IS THE ABILITY OF MACHINES TO
REPLICATE OR ENHANCE HUMAN INTELLECT, SUCH AS REASONING AND
LEARNING FROM EXPERIENCE. ARTIFICIAL INTELLIGENCE HAS BEEN USED
IN COMPUTER PROGRAMS FOR YEARS, BUT IT IS NOW APPLIED TO MANY
OTHER PRODUCTS AND SERVICES.

FEATUERS:
- FACIAL RECOGNITION
- DEEP LEARNING
- AUTOMATE TASKS
- DATA INGESTION
INTRODUCTION TO PYTHON AND USE OF
ARTIFICIAL INTELLIGENCE IN PYTHON :

Python is an interpreted, object-oriented, high-level programming


language with dynamic semantics developed by Guido van Rossum.
USE OF ARTIFICIAL INTELLIGENCE IN PYTHON:

Python is a key part of AI programming languages due to the fact that


it has good frameworks, such as scikit-learn-Machine Learning in
Python that meets almost all requirements in this area . It is among the
most efficient and user-friendly tools to visualize.
Python Libraries for General Artificial Intelligence:

NLTK

AIMA

TensorFlow

Keras
USE OF MATPLOTLIB IN PYTHON

Matplotlib is a low-level library of Python which is used for


data visualization. It is easy to use and emulates MATLAB
like graphs and visualization. This library is built on the top
of NumPy arrays and consist of several plots like line chart,
bar chart, histogram, etc.
How to import?
#importing pyplot module from matplotlib from matplotlib
import pyplot as plt
#or
import matplotlib.pyplot as plt
USE OF NUMPY IN PYTHON

NumPy is a Python library used for working with arrays.


It also has functions for working in domain of linear
algebra, fourier transform, and matrices. NumPy was
created in 2005 by Travis Oliphant. It is an open source
project and you can use it freely.
How to import NumPy
Import numpy as np
USE OF PANDAS IN PYTHON

Pandas is an open source Python package that is most


widely used for data science/data analysis and machine
learning tasks. It is built on top of another package
named Numpy, which provides support for multi-
dimensional arrays.
HOW TO IMPORT PANDAS?
Import pandas as pd
MACHINE LEARNING

Machine learning is a subfield of


artificial intelligence (AI). The goal of
machine learning generally is to
understand the structure of data and fit
that data into models that can be
understood and utilized by people.
Although machine learning is a field
within computer science, it differs from
traditional computational approaches.
PROJECT 1:
DIGITAL CLASSIFICATION WITH CNN :
IN THIS , I HAVE CREATED A DEEP CONVOLUTIONAL NEURAL NETWORK (CNN) MODEL TO RECOGNIZE DIFFERENT
HANDWRITTEN DIGITS AND CLASSIFY THEM. THE DATASET USED HERE IS TRUE DATASET AND FAKE DATASET.
A CNN IS A KIND OF NETWORK ARCHITECTURE FOR DEEP LEARNING ALGORITHMS AND IS SPECIFICALLY USED FOR IMAGE
RECOGNITION.

DATASET PROVIDED : OUTPUT :


PROJECT 2:
NEWS CLASSIFICATION USING NATURAL LANGUAGE PROCESSING :
DETECTING TRUE NEWS AND CLASSIFICATION OF FAKE NEWS USING MACHINE LEARNING APPROACHES PROPOSED NEURAL
NETWORKS AND CONVOLUTIONAL NEURAL NETWORK TO FIND OUT GIVEN NEWS IS FAKE OR REAL.

DATASET PROVIDED : OUTPUT :


PROJECT 3 :
CELEBRITY IMAGE CLASSIFIER :
IN THIS PROJECT , WE HAVE TO UPLOAD AN IMAGE OF A SPORTS CELEBRITY (LIONEL MESSI, MARIA SHARAPOVA, ROGER
FEDERER, SERENA WILLIAMS, VIRAT KOHLI) AND IT PREDICTS WHOSE IMAGE IS UPLOADED. CELEBRITY IMAGE CLASSIFIER
COMES UNDER FACE RECOGNITION. FACE RECOGNITION IS A COMPUTER APPLICATION THAT IS CAPABLE OF TRACKING ,
DETECTING , TRACKING AND IDENTIFYING HUMAN FACES FROM AN IMAGE CAPTURED USING A DIGITAL CAMARA.
IMPLEMENTATION-VISUALIZATION:

MATPLOTLIB CNN CLASSIFICATION IMAGE CLASSIFICATION


1. True Dataset:
https://www.kaggle.com/datasets/srishtysinha/truecsv

2. Fake Dataset:
https://www.kaggle.com/datasets/deepakbhandare/fakecsv

3. Project Explaination Link:


https://student.1stop.ai/lms#
1. After completing this internship , I have learnt about Artificial Intelligence and also learnt about how
Artificial Intelligence is used in Python..
2. In the Mini project1 I had learnt how a dataset is divided into training and test dataset. As an
example, a popular dataset called MNIST was taken to make predictions of handwritten digits from 0
to 9. The dataset was cleaned, scaled, and shaped. Using TensorFlow, a CNN model was created and
was eventually trained on the training dataset. Finally, predictions were made using the trained
model.
3. In the Mini project-2 I have learnt Fake news detection techniques i.e.; it can be divided based on
style and those based on content, or fact-checking. Too often it is assumed that bad style (bad
spelling, bad punctuation, limited vocabulary, using terms of abuse, grammatically, etc.) is a safe
indicator of fake news.

4. In the Celebrity image classifier project, OpenCV haarcascade was used to detect face and two eyes.
Wavelet transform was used to extract these features from the images. At last after processing and
cleaning the data, it was given as input to models. Finally we obtained 99% accuracy using CNN in
Sports Image Classifier.
THANK YOU

You might also like