INTERNSHIP REPORT

A report submitted in partial fulfillment of the requirements of

BACHELOR OF TECHNOLOGY
in
COMPUTER SCIENCE AND ENGINEERING – ARTIFICIAL
INTELLIGENCE
by

Name:Uttkarsh Dwivedi

Roll No: 2101921520186

Under Supervision of

Mr. Rudra Kumar

Sinha

(Duration: April 2024 to June 2024)

G.L. BAJAJ INSTITUTE OF TECHNOLOGY & MANAGEMENT,

GREATER NOIDA
Affiliated to

DR. A.P.J. ABDUL KALAM TECHNICAL UNIVERSITY,

LUCKNOW
2024-2025
1
 Declaration

We hereby declare that the internship work presented in this report entitled “AI-ML Virtual
Intership”, in partial fulfillment of the requirement for the award of the degree of Bachelor of
Technology in Computer Science & Engineering, submitted to A.P.J. Abdul Kalam Technical
University, Lucknow, is based on our own work carried out at Department of Computer Science
& Engineering-Artificial Intelligence, G.L. Bajaj Institute of Technology & Management,
Greater Noida. The work contained in the report is true and original to the best of our knowledge
and internship work reported in this report has not been submitted by us for award of any other
degree or diploma.

Signature:
Name: Uttkarsh Dwivedi

Roll No: 2101921520186

2
Certificate of Internship

3
 ACKNOWLEDGEMENT
First and foremost, I would like to express my heartfelt gratitude to AICTE Eduskill and the
AIML Virtual Internship program for providing me with this invaluable learning opportunity.

It is with immense gratitude and a great sense of accomplishment that I acknowledge the
support, knowledge, and opportunities provided by everyone involved in this internship journey.

I pay special thanks to my Head of the Department Dr. Pippal for his constructive criticism
throughout my internship.

I would like to thank Mr.Rudra Kumar Sinha, Internship coordinator for his support and
advise to get and complete internship in above said organization.

I am extremely great full to my department staff members and friends who helped me in
successful completion of this internship.

Name: Uttkarsh Dwivedi

Roll No.:2101921520186

4
 TABLE OF CONTENT

Declaration.................................................................................................................................(ii)
Certificate..................................................................................................................................(iii)
Acknowledgement.....................................................................................................................(iv)
Table of Content........................................................................................................................(v)
Chapter 1. Introduction ................................................................................................. Pg.No.6

Chapter 2. Motivation………………………...….......................................................... Pg.No 7

Chapter 3.Plan of Work………………………………………………………………. Pg No.8

Pg No. 12
Chapter 3. Methodology……………………………………………………………….

Chapter 3. Conclusion, Limitation & Future Scope ……………………………….. Pg No. 18

References..........................................................................................................................Pg.No 19

5
 INTRODUCTION
Google is the world’s most comprehensive and broadly adopted cloud platform, offering over 200 fully
featured services from data centers globally. Millions of customers— including the fastest-growing
startups, largest enterprises, and leading government agencies—are using GOOGLE to lower costs,
become more agile, and innovate faster. GOOGLE provides extensive and detailed documentation for
each GOOGLE service. Guides and application programming interface (API) references are organized by
service category. There are also many general resources and tutorials that can be accessed from the
GOOGLE Documentation pages. This exam covers four domains, including cloud concepts, security,
technology, and billing and pricing.

GOOGLE AI-ML:

In this course we learn

• Recognize how machine learning and deep learning are part of artificial intelligence

• Describe artificial intelligence and machine learning terminology

• Identify how machine learning can be used to solve a business problem

• Describe the machine learning process

• List the tools available to data scientistss

• Identify when to use machine learning instead of traditional software development methods
• Formulate a problem from a business request

• Obtain and secure data for machine learning

• Use Google Cloud to build a Jupyter notebook

• Outline the process for evaluating data

• Explain why data must be preprocessed

• Use open-source tools to examine and preprocess data

• Use TensorFlow to train and host a machine learning model

• Finally, we will learn how to use managed Google ML services to solve specific machine learning

6
 problems in forecasting, computer vision, and natural language processing.

Machine Learning Job Role

• Data Scientist role

• Machine Learning Engineer

• Applied Science Researcher

• Machine learner developed role

7
 Motivation
In today’s data-driven world, businesses and industries generate vast amounts of data that, when properly
analyzed, can unlock valuable insights. However, traditional methods of data analysis are often insufficient
to handle the complexity, scale, and speed of this data. This creates the need for Artificial Intelligence
(AI) and Machine Learning (ML), which can effectively process and analyze large datasets to make
accurate predictions and automate decision-making.

The problem addressed by this internship was to develop practical AI/ML models capable of solving
realworld problems such as spam detection, fraud detection, and personalized recommendations. These
challenges involve processing unstructured data, handling missing or noisy data, and building models that
can generalize well to new, unseen data.

By leveraging AI/ML technologies, the goal was to enhance the ability to identify patterns, improve
efficiency, and make data-driven decisions that can provide a competitive edge across various industries.

8
 Plan of Work

1. Understanding the Basics of AI/ML o

Objective: Familiarize myself with core concepts of Artificial Intelligence (AI)
and Machine Learning (ML).
o Activities:
 Study the definitions and applications of AI and ML, focusing on their real-
world uses.
 Learn about key machine learning algorithms (e.g., Linear Regression, Decision
Trees, Random Forests, Support Vector Machines).
 Explore the differences between supervised, unsupervised, and
reinforcement learning techniques.
 Understand the process of model training, validation, and testing.
2. Data Collection and Preprocessing o
Objective: Prepare and clean data for training machine learning models.
o Activities:
 Dataset Selection: Identify relevant datasets that align with the internship goals,
such as datasets for spam detection, recommendation systems, or fraud detection.
 Data Cleaning: Use Python libraries like Pandas and NumPy to handle missing
values, remove duplicates, and detect outliers.
 Feature Engineering: Select the most relevant features from the dataset and
perform feature extraction or transformation as needed.
 Data Normalization/Standardization: Scale numerical features to ensure uniformity
and avoid bias in model training.
3. Model Building o
Objective: Build machine learning models to solve identified problems.
o Activities:
 Algorithm Selection: Choose appropriate algorithms based on the problem
(e.g., Decision Trees for classification, k-means for clustering).
9
  Model Development: Use frameworks like Scikit-learn for traditional machine
learning models and TensorFlow/Keras for deep learning models.
 Model Training: Split the dataset into training and testing sets. Use train_test_split
to ensure unbiased model evaluation.
 Model Evaluation Metrics: Evaluate models based on accuracy, precision,
recall, F1score, confusion matrix, etc., to gauge the model's performance.
4. Model Evaluation and Tuning o
Objective: Improve model accuracy and performance through fine-tuning.
o Activities:
 Cross-Validation: Implement K-fold cross-validation to ensure the
model’s robustness and generalization.
 Hyperparameter Tuning: Use techniques like GridSearchCV or
RandomizedSearchCV to identify the best hyperparameters for the chosen
algorithms.
 Model Comparison: Compare different models and select the one that performs
best based on evaluation metrics.
 Overfitting/Underfitting: Ensure that the model is neither overfitting nor underfitting
by analyzing performance on the training vs testing data.
5. Deployment and Integration o
Objective: Deploy the trained model and integrate it into a real-world
application.
o Activities:
 Cloud Deployment: Deploy the model on cloud platforms like Google Cloud or
use Google Colab for easy accessibility and GPU acceleration.
 Model Integration: Integrate the model into applications like spam filters,
recommendation systems, or fraud detection systems. Implement REST APIs for
easy interaction with other systems.
 Performance Monitoring: Track model performance post-deployment to ensure
that it continues to meet business requirements and adapt as necessary.

10
6. Documentation and Reporting o
Objective: Document the internship process, outcomes, and learning.
o Activities:
 Process Documentation: Document each step of the workflow—data collection,
preprocessing, model selection, training, tuning, and deployment.
 Results and Insights: Prepare detailed reports summarizing the insights gained
from the models, including performance metrics, challenges faced, and solutions
implemented.
 Presentation: Prepare a final presentation of the internship, including a
demonstration of the model and its real-world applications.

11
 Methodology

GOOGLE Machine Learning

Welcome to GOOGLE Academy Machine Learning.
Data scientist role:
• Applying knowledge of statistics and analytical skills to interpret data

• Data scientists often have degrees in statistics, computer science, or economics Machine learning engineer:

• Emphasis on programming and system design skills

• Often have background as a developer or software architech Applied science researcher: • Applies

machine learning technology to a specific domain

• Requires knowledge of both the domain and machine learning Machine learning developer role:

• Integrating machine learning with software applications

• Requires strong application development skills and machine learning knowledge

Introducing Machine Learning

• Artificial intelligence is the broad field of building machines to perform human tasks

• Machine learning is a subset of AI. It focuses on using data to train ML models so themodels can
make predictions.

• Deep learning is a technique that was inspired from human biology. It uses layers of neurons to
build networks that solve problems.

• Advancements in technology, cloud computing, and algorithm development have led to a rise
inmachine learning capabilities and applications.

• Machine learning applications are already part of your everyday life.

• The machine learning stack has three key layers.

• API services, machine learning services, and machine learning frameworks

• Machine learning development is different from traditional development

12
 • You will face many machine learning challenges. The biggest problems that you directly influence
are related to data,but you will also deal with people, business and technology challenges.

• Consider managed services to help you solve machine learning problems.

• The machine learning pipeline describes the different stages for developing a machine learning application.

• The machine learning stack has three key layers.

• API services, machine learning services, and machine learning frameworks Machine learning

development is different from traditional development.

• Training algorithms are applied to data to create a model for making predictions.

• Machine learning is a subset of artificial intelligence.

• Machine learning applies learning algorithms to develop models from large datasets.

Business Problems Solved With Machine Learning

Machine learning is used throughout a person’s digital life. Here are some examples:

• Spam – Your spam filter is the result of an ML program that was trained with examples of spam and
regular email messages.

• Recommendations –Based on books that you read or products that you buy, ML programs predict other
books or products that you might want. Again, the ML program was trained with data from other
readers’ habits and purchases.

• Credit card fraud –Similarly, the ML program was trained on examples of transactions that turned out to
be fraudulent, along with transactions that were legitimate.
Machine learning applications are already part of your everyday life.

• The first step is to get your data into a format that can be used easily.

• Pandas is a popular and useful Python library for working with data.

13
• Descriptive statistics help you gain insights into the data.

• Use visualizations to examine the dataset in more detail.

• Feature engineering involves selecting or extracting the best features for machine learning.

• Preprocessing gives you better data to work with. Better data typically provides better results.

• Preprocessing has two categories:

• Develop a strategy for dirty data. Replace or delete rows with missing data.

• Delete, transform, or impute new values for outliers.

• Split data into training, testing and validation sets to help you validate the models accuracy

• Can use K-fold cross validation can help with smaller datasets

• Can use two key algorithms for supervised learning—XGBoost and linear learner

• Use k-means for unsupervised learning

AI is about building machines that can perform tasks that a human would typically perform. In modern culture, AIs
appear in movies or works of fiction. You might recall some AIs in science fiction movies or TV shows that
control the future world, or act intelligently on their own sometimes, with negative effects for society or the human
beings around them. These AIs started as computer agents that perceived their environments and took actions to
achieve a specific goal. However, for some of these fictional AIs, their actions were not the outcome that their
creators had
14
originally envisioned. Other fictional AIs are more benign or positive: they do a better job working with
humanity, but they are also more general in purpose. These kinds of general AIs are examples of Artificial
General
Intelligence (AGI). They have the capability to learn or understand any task that a human being can understand. AI
problems typically span many fields of research: natural language processing, reasoning, knowledge representation,
learning, perception, and physical environment interaction. AI isn’t yet a reality, unless you are living in a
simulation. However, it gets closer in each of these areas each year.
Machine Learning Machine learning is the scientific study of algorithms and statistical models to perform a task by
using inference instead of instruction
Tom Mitchell, a pioneer of machine learning, wrote this definition: “A computer program is said to learn from
experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as
measured by P, improves with experience E.”
(Mitchell, Tom. 1997. Machine Learning. McGraw Hill. p.2.)
If you apply this concept to spam, the letters E, T, and Prepresent:
• E –The email messages that indicate spam or not

• T –The task of identifying spam

• P –The probability that the unseen email message is spam

Introduction to Forecasting
• Timeseries data is sequenced data that includes a time element, which makes it different from
regular datasets

• Some of the time challenges include–

• Handling different time formats

• Handling missing data through down sampling, up sampling and smoothing

• Handling seasonality, such as weekdays and yearly cycles

• Avoiding bad correlations

• The pandas library offers support for time series data through functions that deal with time

• With Google Forecast, you can choose between five algorithms– • You can use Google Forecast to

trainand use a model for time series data

• There are specific schemas defined for domains such as retail and Google Cloud capacity planning, or you
canuse a custom schema

15
• You need to supply at least the time series data, but can also provide metadata and related data to
addmove information to the model
• As with most supervised machine learning problems, your data is split into training and testing data,but
this split takes into account the time element

• Use RMSE and w Quantile Loss metrics to evaluate the efficiency of the model

Introduction to computer vision

• Computer vision is the automated extraction of information from images

• From a practical point of view, you can divide computer vision into two distinct areas— image
analysisand video analysis
• Hyperparameters can be tuned for the model, optimizer, and data.

• Google Vertex AI can perform automatic hyperparameter tuning.

• Overall model development can be accelerated by using Autopilot

• Google Recognition provides image and video detection of faces, sentiment, text, unsafe content,
andlibrary search.

• Google Recognition is integrated into other Amazon services.

• Models must be trained for the specific domain that you want to analyze

• You can set custom labeling for the specific business case

• Custom labeling workflow

• You must label images and create bounding boxes for objects

• You can use Google Vertex AI Ground Truth to build training datasets for your models

Introducing Natural Language Processing

• As a domain, NLP predates machine learning

• NLP development maps directly to the ML development process.

16
• Some of the main use cases for NLP are search query analysis, human-machine interaction, and marketor
social research.

• NLP is difficult because of the imprecise nature of human language.

• Google Transcribe can automatically convert spoken language to text

• Google Translate can convert written text to spoken language

• Google Translate can create real-time translation between languages

17
 CONCLUSION

GOOGLE AI ML described how model explainability relates to AI/ML solutions, giving customers insight to
explainability requirements when initiating AI/ML use cases. To help convey how these model explainability
options relate to real-world scenarios, examples from a range of industries were demonstrated.
• It is recommended that AI/ML owners or business leaders follow these steps when initiating a new
AI/ML solution:

• Collect business requirements to identify the level of explainability required for your business toaccept
the solution.

• Based on business requirements, implement an assessment for model explainability.

• Work with an AI/ML technician to communicate model explainability assessment andfind theoptimal
AI/ML solution to meet your business objectives.
• After the solution is completed, revisit the model explainability assessment to
evaluatethatbusiness requirements are continuously met.

• Bytaking these steps, you will mitigate regulation risks and ensure trust in your model.Machine Learning on
GOOGLE. Get deeper insights from your data while lowering costs with GOOGLE machine learning (ML).
GOOGLE helps you at every stage of your ML adoption journey with the most comprehensive set of
artificial intelligence ML services, infrastructure, and implementation resources.

18
 REFERENCES
1. Grow with Google. (n.d.). Retrieved from https://grow.google/intl/en_in/

19