Summer Internship Report

AI-ML Virtual Internship

EduSkills on AICTE Internship Portal

Submitted By:

FAREHA TABASSUM

ROLL.NO:
160519733031

Department of Computer Science & Engineering

At

International Airport Road, Chandrayangutta,

Bandlaguda, Hyderabad - 500 005.
 CERTIFICATE

This is to certify that the work entitled “ AWS-AI ML VIRTUAL INTERNSHIP“ is a

bonafide work of FAREHA TABASSUM, bearing H. T. No.160519733031 ,submitted in partial

fulfilment of the requirement for the award of the degree of BACHELOR OF ENGINEERING in

COMPUTER SCIENCE & ENGINEERING during the academic year 2022-2023.

This is further certified that the work done under our guidance, and the results of this work have not

been submitted elsewhere for the award of any of the degree.

Internal guide External Examiner HOD

Dr. Jameel Hashmi Dr. Mohammed Abdul Bari

2
 Acknowledgment

It is a proud privilege and duty to acknowledge the kind of help and guidance received from several

people during this course. It would not have been possible without their valuable help, cooperation

and guidance. I wish to record my sincere gratitude to Dr. MOHAMMED ABDUL BARI, and Dr.

PATHAN AHMED KHAN for their constant support. The course on “AWS AI-ML VIRTUAL

INTERNSHIP” was very helpful in giving the necessary background information and inspiration.

Their contributions and technical support are greatly acknowledged.

FAREHA TABASSUM
160519733031

3
CERTIFICATE

4
 TABLE OF CONTENTS

S.no Title Pg.no

01 Certificate 2

02 Acknowledgment 3

03 Domain Of Internship 6-7

04 Introduction & Technological Details

1 Introduction: 8-9
1.1 What is “machine learning ”?
1.2 Business Problems solved with Machine
Learning
2 Implement Machine Learning Pipeline: 10-13
2.1 Introduction to ML Pipeline
2.2 Implementation Using SageMaker
3 Forecasting: 14-15
3.1 Introduction to Forecasting
3.2 Processing time-series data
3.3 Using Amazon Forecast

4 Computer Vision: 16-19

4.1 Introduction to computer vision
4.2 Analyzing images and videos
4.3 Preparing custom datasets for CV

5 Natural Language Processing: 20-23

5.1 Introducing Natural Language Processing
5.2 Managed Services

05 Output Screens 24-25

06 Conclusion 26
07 References 28
5
 CLOUD COMPUTING

Cloud Computing can be defined as the practice of using a network of remote servers hosted on the
Internet to store, manage, and process data, rather than a local server or a personal computer.
Companies offering such kinds of cloud computing services are called cloud providers and typically
charge for cloud computing services based on usage. Grids and clusters are the foundations for cloud
computing.

Types of Cloud Computing:

Most cloud computing services fall into five broad categories:

1. Software as a service (SaaS)

2. Platform as a service (PaaS)
3. Infrastructure as a service (IaaS)
4. Anything/Everything as a service (XaaS)
5. Function as a Service (FaaS)

These are sometimes called the cloud computing stack because they are built on top of one
another. Knowing what they are and how they are different, makes it easier to accomplish your goals.
These abstraction layers can also be viewed as a layered architecture where services of a higher layer
can be composed of services of the underlying layer i.e, SaaS can provide Infrastructure.

• Software as a Service(SaaS)
Software-as-a-Service (SaaS) is a way of delivering services and applications over the
Internet. Instead of installing and maintaining software, we simply access it via the Internet,
freeing ourselves from the complex software and hardware management. It removes the need to
install and run applications on our own computers or in the data centers eliminating the expenses
of hardware as well as software maintenance.
SaaS provides a complete software solution that you purchase on a pay-as-you-go basis
from a cloud service provider. Most SaaS applications can be run directly from a web browser
without any downloads or installations required. The SaaS applications are sometimes called
Web-based software, on-demand software, or hosted software.
Advantages of SaaS
• Cost-Effective: Pay only for what you use.
• Reduced time: Users can run most SaaS apps directly from their web browser without
needing to download and install any software. This reduces the time spent in installation and
configuration and can reduce the issues that can get in the way of the software deployment.
• Accessibility: We can Access app data from anywhere.
• Automatic updates: Rather than purchasing new software, customers rely on a SaaS
provider to automatically perform the updates.

6
• Scalability: It allows the users to access the services and features on-demand.
The various companies providing Software as a service are Cloud9 Analytics,
Salesforce.com, Cloud Switch, Microsoft Office 365, Big Commerce, Eloqua, dropBox, and
Cloud Tran.

• Platform as a Service
PaaS is a category of cloud computing that provides a platform and environment to
allow developers to build applications and services over the internet. PaaS services are hosted
in the cloud and accessed by users simply via their web browser.
A PaaS provider hosts the hardware and software on its own infrastructure. As a
result, PaaS frees users from having to install in-house hardware and software to develop or
run a new application. Thus, the development and deployment of the application take place
independent of the hardware.
The consumer does not manage or control the underlying cloud infrastructure
including network, servers, operating systems, or storage, but has control over the deployed
applications and possibly configuration settings for the application-hosting environment. To
make it simple, take the example of an annual day function, you will have two options either
to create a venue or to rent a venue but the function is the same.

The various companies providing Platform as a service are Amazon Web services
Elastic Beanstalk, Salesforce, Windows Azure, Google App Engine, cloud Bess and IBM
smart cloud.

• Infrastructure as a Service:
Infrastructure as a service (IaaS) is a service model that delivers computer
infrastructure on an outsourced basis to support various operations. Typically IaaS is a service
where infrastructure is provided as outsourcing to enterprises such as networking equipment,
devices, database, and web servers.
It is also known as Hardware as a Service (HaaS). IaaS customers pay on a per-user
basis, typically by the hour, week, or month. Some providers also charge customers based on
the amount of virtual machine space they use.
It simply provides the underlying operating systems, security, networking, and servers
for developing such applications, and services, and deploying development tools, databases,
etc.

7
 1. INTRODUCTION

Machine learning (ML) is a type of artificial intelligence (AI) that allows software applications to
become more accurate at predicting outcomes without being explicitly programmed to do so.
Machine learning algorithms use historical data as input to predict new output values. Machine
learning algorithms allow computers to train on data inputs and use statistical analysis to output
values that fall within a specific range. Because of this, machine learning facilitates
Computers build models from sample data to automate decision-making processes based on data
inputs.

1.1 What is “MACHINE LEARNING”?

Machine learning is an application of artificial intelligence (AI) that provides systems the ability to
automatically learn and improve from experience without being explicitly
programmed. Machine learning focuses on the development of computer programs that can access
data and use it to learn for themselves.

1.2 Types of Machine Learning

Fig: 1 Classification of Machine Learning

8
 1. Supervised Learning:
• Supervised learning as the name indicates the presence of a supervisor as a teacher.
• We teach or train the machine using data which is well labeled.(that
means some data is already tagged with the correct answer)
• Once the training is done, The machine is fed with new test data, Using
which, the Accuracy of the particular learning algorithm is tested.
2. Unsupervised Learning:

• Unlike supervised learning, input data in unsupervised learning doesn’t

have any labels Associated with it.
• The machine itself identifies the underlying structure of the data, to identify similar
patterns.
• The data which is similar in nature, or has similar properties, is grouped together.

3. Reinforcement Learning:
• The machine learns through a system of rewards and punishments.
• The goal of the machine is to maximize the total reward and avoid punishment

1.2 Business Problems solved with Machine Learning

You can use Amazon Machine Learning to apply machine learning to problems for
which you have existing examples of actual answers. For example, if you want to use
Amazon Machine Learning to predict if an email is spam, you will need to collect email
examples correctly labeled as spam or not. You then can use machine learning to generalize
from these email examples to predict how likely new email is spam or not. This approach of
learning from data that has been labeled with the actual answer is known as supervised
machine learning. You can use supervised ML approaches for these specific machine learning
tasks: binary classification (predicting one of two possible outcomes), multiclass
classification (predicting one of more than two outcomes) and regression (predicting a
numeric value.
● 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.

9
 2.IMPLEMENT MACHINE LEARNING PIPELINE

2.1 Introduction to ML Pipeline:

● A machine learning pipeline is the end-to-end construct that orchestrates the

flow of data into, and output from, a machine learning model (or set of
multiple models). It includes raw data input, features, outputs, the machine
learning model and model parameters, and prediction outputs.
● The machine learning pipeline is an iterative process. When you work on a
real-world problem, you might iterate many times before you find a solution
that meets the business needs

Fig 2 : AWS Pipeline Architecture

2.2 Implementation Using SageMaker:

Section 1:

● In this first section, you examine how to think about turning a business
requirement into a machine learning problem.
● Business problems must be converted into an ML problem.
● Questions to ask while doing so include
○ Have we asked why enough times to get a solid business problem
statement and know why it is important?
○ Can you measure the outcome or impact if your solution is implemented?
● Most business problems fall into one of two categories –
○ Classification (binary or multi): Does the target belong to a class?
○ Regression: Can you predict a numerical value

10
Section 2:

● In this section, you will explore some of the techniques and challenges
involved with collecting and securing the data that you need for machine
learning.
● The first step in solving machine learning problems is to obtain data that
is required to train your machine learning model.
● ETL can be used to obtain data from multiple sources.
● Services such as AWS Glue can make it easy to obtain data from multiple data
stores.
● Security requirements should be understood, and they should be based on
both business needs and any regulatory requirements. You want to ensure
that your data is secure, only authorized users can access it, and it is
encrypted where possible.

Section 3:

● In this section, you learn how to evaluate data for machine learning. You
look at different data formats and types, and how you can visualize and
analyze the data before feature engineering
● 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.
● Descriptive statistics help you gain insights into the data.
● Use visualizations to examine the dataset in more detail.

Section 4:

● In this section, you look at the key task of feature engineering, which
selects the columns of data that make the most impact in the model.
● 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:
○ Converting data (to numerical values)
○ Cleaning up dirty data (removing missing data, cleaning outliers)
● How you deal with dirty data affects your model, pay attention to missing data and
outliers.
● Develop a strategy for dirty data. Replace or delete rows with missing data.
○ Delete, transform, or impute new values for outliers.

11
Section 5:

● In This section, you will learn how to select a model and train it
with the data that you preprocessed.
● 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•Use Amazon SageMaker training jobs to
train models

Section 6:

● In this section, you will learn how you can deploy your trained model
for consumption by applications.
● You can deploy your trained model by using Amazon SageMaker to
handle API calls from applications, or to perform predictions by using a
batch transformation.
● The goal of your model is to generate predictions to answer the business
problem. Be sure that your model can generate good results before you
deploy it to production.
● Use Single-model endpoints for simple use cases and use multi-model
endpoint support to save resources when you have multiple models to deploy

Section 7:

● In this section, you will learn how you can evaluate your model’s success in
predicting results.
● To evaluate the model, you must have data that the model hasn’t seen,
through either a hold-out set or by using k-fold cross validation.
● Different machine learning models use different metrics.
○ Classification can use confusion matrix, and the AUC-ROC that can
be generated from it.
○ Regression can use mean squared.

Section 8:

● In this section, you will learn how to tune the model’s hyperparameters
to improve model performance
● Model tuning is important to find the best solution to your business problem.
● Hyperparameters can be tuned for the model, optimizer, and data.
● Amazon SageMaker can perform automatic hyperparameter tuning.
Overall model development can be accelerated by using Autopilot.

12
2.3 Summary:

In summary, in this module, you learned how to:

● Formulate a problem from a business request
● Obtain and secure data for machine learning (ML)
● Build a Jupyter Notebook by using Amazon SageMaker
● Outline the process for evaluating data
● Explain why data must be preprocessed
● Use open source tools to examine and preprocess data
● Use Amazon SageMaker to train and host an ML model
● Use cross-validation to test the performance of an ML model
● Use a hosted model for inference
● Create an Amazon SageMaker hyperparameter tuning job to optimize a model’s
effectiveness.

13
 3. FORECASTING

3.1 Introduction to Forecasting:

● Forecasting is an important area of machine learning. It is important

because so many opportunities for predicting future outcomes are
based on historical data.
● You can think of time series data as falling into two broad categories.
● The first type is univariate, which means that it has only one variable.
● The second type is multivariate, which means that it has more than one variable.
● In addition to these two categories, most time series datasets also follow
one of the following patterns.
● Trend –A pattern that shows the values as they increase, decrease, or stay the same
over time
● Seasonal –A repeating pattern that is based on the seasons in a year
● Cyclical –Some other form of a repeating pattern
● Irregular –Changes in the data over time that appear to be random or that
have no discernable pattern

You can use forecasting for a range of domains. Some of the more common applications
include:
● Marketing applications, such as sales forecasting or demand projections.
● Inventory management systems to anticipate required inventory levels.
Often, this type of forecast includes information about delivery times.
● Energy consumption to determine when and where energy is needed.
● Weather forecasting systems for governments, and commercial applications such as
agriculture.

3.2 Processing time series data:

● Time Series 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 Amazon Forecast, you can choose between five algorithms.
○ ARIMA
○ DeepAR+
○ ETS
○ NPTS
○ Prophet

14
3.3 Using Amazon Forecast:

● You can use Amazon Forecast to train and use a model for time series data
● There are specific schemas defined for domains such as retail and EC2
capacity planning, or you can use a custom schema
● You need to supply at least the time series data, but can also provide
metadata and related data to add move 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 wQuantileLoss metrics to evaluate the efficiency of the model

Summary:
● In summary, in this module you learned how to:
● Describe the business problems solved by using Amazon Forecast
● Describe the challenges of working with time series data
● List the steps that are required to create a forecast by using Amazon Forecast
● Use Amazon Forecast to make a prediction

15
 4. COMPUTER VISION

4.1 Introduction to computer vision:

• You can think of computer vision as the automated extraction of information

from digital images
• Computer vision enables machines to identify people, places, and things in
images with accuracy at or above human levels, with greater speed and
efficiency.
• The image data can take many forms, such as single images, video sequences,
views from multiple cameras, or three-dimensional data.

Some of the primary use cases for computer vision include these examples.
● Public safety and home security: Computer vision with image and facial
recognition can help to quickly identify unlawful entries or persons of
interest. This process can result in safer
communities and a more effective way of deterring crimes.
● Authentication and enhanced computer-human interaction: Enhanced human-
computer
interaction can improve customer satisfaction. Examples include products
that are based on customer sentiment analysis in retail outlets or faster
banking services with quick
authentication that is based on customer identity and preferences.
● Content management and analysis: Millions of images are added every
day to media and social channels. The use of computer vision
technologies—such as metadata extraction and image classification—can
improve efficiency and revenue opportunities.
● Autonomous driving: By using computer-vision technologies, auto
manufacturers can provide improved and safer self-driving car navigation,
which can help realize autonomous driving and make it a reliable
transportation option.
● Medical imaging: Medical image analysis with computer vision can
improve the accuracy and speed of a patient's medical diagnosis, which can
result in better treatment outcomes and life
expectancy.
● Manufacturing process control: Well-trained computer vision that is
incorporated into robotics can improve quality assurance and
operational efficiencies in manufacturing
applications. This process can result in more reliable and cost-effective products

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 analysis
○ video analysis

16
 ● Image analysis includes object classification, detection, and segmentation
● Video analysis includes instance tracking, action recognition, and motion
estimation

4.2 Analyzing images and videos:

● Amazon Rekognition is a computer vision service based on deep learning.

You can use it to add image and video analysis to your applications.
● Amazon Rekognition enables you to perform the following types of analysis:
○ Searchable image and video libraries– Amazon Rekognition makes
images and
stored videos searchable so that you can discover the objects and
scenes that appear in them.
○ Face-based user verification– Amazon Rekognition enables your
applications to
confirm user identities by comparing their live image with a reference
image.
○ Sentiment and demographic analysis– Amazon Rekognition
interprets emotional expressions, such as happy, sad, or surprise.
It can also interpret demographic information from facial images,
such as gender.
○ Unsafe content detection–Amazon Rekognition can detect
inappropriate content in images and stored videos
○ Text detection–Amazon Rekognition Text in Image enables
you to recognize and extract text content from images
● Amazon Rekognition is integrated into other AWS services.

4.3 Preparing custom datasets for computer vision:

● 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
● The bounding box coordinates show where the object is located on the
source image. The coordinate values are a ratio of the overall image
size.
● You can use Amazon SageMaker Ground Truth to build training datasets for
your models.

4.3.2 Amazon SageMaker Ground Truth:

● Amazon SageMaker provides two data labeling offerings,
○ Amazon SageMaker Ground Truth Plus
○ Amazon SageMaker Ground Truth.
● Both options allow you to identify raw data, such as images, text files, and
videos, and add informative labels to create high-quality training datasets
for your machine learning models.

17
Amazon SageMaker Ground Truth Plus

● With SageMaker Ground Truth Plus, you can easily create high-quality
training datasets without having to build labeling applications or manage
labeling workforces on your own.
● Amazon SageMaker Ground Truth Plus helps reduce data labeling costs by up to
40%.
Amazon SageMaker Ground Truth Plus provides an expert workforce
that is trained on ML tasks and can help meet your data security, privacy,
and compliance requirements.
● You simply upload your data, and Amazon SageMaker Ground Truth Plus then
creates data
labeling workflows and manages workflows on your behalf.
● The image below depicts the workflow of Amazon Pagemaker ground truth Plus:

Fig 3: SageMaker Working

18
Amazon SageMaker Ground Truth

● If you want the flexibility to build and manage your data labeling workflows
and manage your data labeling workforce, you can use Amazon SageMaker
Ground Truth.
● SageMaker Ground Truth is a data labeling service that makes it easy to
label data and gives you the option to use human annotators through
Amazon Mechanical Turk, third-party
vendors, or your private workforce.
● the image below depicts the workflow of Amazon SageMaker ground Truth

Fig 4: Ground Truth

19
 5. NATURAL LANGUAGE PROCESSING

5.1 Introduction to natural language processing:

NLP is a broad term for a general set of business or computational problems that you
can solve with machine learning (ML). NLP systems predate ML. Two examples are
speech-to-text on your old cell phone and screen readers. Many NLP systems now
use some form of machine learning. NLP considers the hierarchical structure of
language. Words are at the lowest layer of the hierarchy. A group of words makes a
phrase. The next level up consists of phrases, which make a sentence, and ultimately,
sentences convey ideas.

Fig 5: How NLP works

Some of the main challenges for NLP include:

● Discovering the structure of the text – One of the first tasks of any
NLP application is to break the text into meaningful units, such as
words, phrases, and sentences.
● Labeling data – After the system converts the text to data, the next challenge is
to apply labels that represent the various parts of speech. Every language
requires a different labeling scheme to match the language’s grammar.
● Representing context – Because word meaning depends on context, any
NLP system needs a way to represent the context. It is a big challenge
because of the large number of contexts.
Converting context into a form that computers can understand is difficult.
● Applying grammar – Although grammar defines a structure for language,
the application of grammar is nearly infinite. Dealing with the variation in
how humans use language is a major challenge for NLP systems.
Addressing this challenge is where machine learning can have a big impact.

20
You can apply NLP to a wide range of problems. Some of the more common
applications include:
● Search applications (such as Google and Bing)
● Human-machinene interfaces (such as Alexa)
● Sentiment analysis for marketing or political campaigns
● Social research that is based on media analysis
● Chatbots to mimic human speech in applications

5.2 Natural language processing managed services:

● There are mainly five managed Amazon ML services that you can use
for various NLP use cases. These services simplify the process of
creating an NLP application.
Amazon Transcribe:
● It can automatically convert spoken language to text.
● You can use Amazon Transcribe to recognize speech in audio files and produce a
transcription.
● Amazon Transcribe can recognize specific voices in an audio file,
and you can create acustomized vocabulary for terms that are
specialized for a particular domain.
● You can also add transcription service to your applications by integrating with
WebSockets.
● WebSockets provide an internet-facing interface that enables two-way
communication between an application and Amazon Transcribe

Some of the more common use cases for Amazon Transcribe include:
● Medical transcription –Medical professionals can record their notes, and
Amazon Transcribe can capture their spoken notes as text.
● Video subtitles –Video production organizations can generate subtitles
automatically from video. It can also be done in real-time for a live feed
to add closed captioning (CC).
● Streaming content labeling –Media companies can capture and label
content, and then feed the content into Amazon Comprehend for further
analysis.
● Customer call center monitoring –Companies can record customer service
or sales calls, and then analyze the results for training or strategic
opportunities.

Amazon Polly:

● It can convert written text to spoken language.

● You can input either plaintext files or a file in Speech Synthesis Markup
Language (SSML) format. SSML is a markup language that you can use
to provide special instructions for how speech should sound.
● For example, you might want to introduce a pause in the flow of speech.
● You can add an SSML tag to instruct Amazon Polly to pause between two words.

21
Some of the more common use cases for Amazon Polly include:
● News service production – Major news companies use Amazon Polly
to generate vocal content directly from their written stories.
● Language training systems –Language training companies use
Amazon Polly to create systems for learning a new language.
● Navigation systems – Amazon Polly is embedded in mapping
application programming interfaces (APIs) so that developers can add
voice to their geo-based applications.
● Animation production – Animators use Amazon Polly to add voices to their
characters
Amazon Translate

It can create real-time translation between languages. You can create systems
for reading documents in one language and then render or store them in another
language. You can also use Amazon Translate as part of a document analysis system.

Some of the more common use cases for Amazon Translate include:
● International websites – You can use Amazon Translate to quickly globalize your
websites.
● Software localization – Localization is a major cost for all software that is
aimed at a global audience. Amazon Translate can decrease software
development time and significantly reduce costs for localizing software.
● Multilingual chatbots – Chatbots are used to create a more human-like interface
to
applications. With Amazon Translate, you can create a chatbot that speaks multiple
languages.
● International media management – Companies that manage media for a
global audience use Amazon Translate to reduce their costs for localization.

Amazon Comprehend

It automates many of the NLP use cases that are reviewed in this module.
Amazon Comprehend implements many of the NLP techniques that you reviewed
earlier in this module. You can extract key entities, perform sentiment analysis, and
tag words with parts of speech.

Some of the more common use cases for Amazon Comprehend include:
● Analysis of legal and medical documents – Legal, insurance, and medical
organizations have used Amazon Comprehend to perform many of the NLP
functions that you learned about in this module.
● Financial fraud detection – Banking, financial, and other institutions have used
Amazon
Comprehending to examine very large datasets of financial transactions to
uncover fraud and look for patterns of illegal transactions.

22
 ● Large-scale mobile app analysis – Developers of mobile apps can use Amazon
Comprehend
to look for patterns in how their apps are used so they can design improvements.
● Content management – Media and other content companies can use
Amazon Comprehend to tag content for analysis and management purposes
Amazon Lex

It can create a human-like interface for your application. Amazon Lex enables you to use
the same
conversational engine that powers Amazon Alexa. You can automatically increase
capacity by creating AWS Lambda functions to scale on demand. In addition, you
can store log files of the conversations for further analysis.

Some of the more common use cases for Amazon Lex include:
● Building frontend interfaces for inventory management and sales –
Voice interfaces are becoming more common. Companies use Amazon
Lex to add chatbots to their inventory and sales applications.
● Developing interactive assistants – By combining Amazon Lex with
other ML services, customers create more sophisticated assistants for
many different industries.
● Creating customer service interfaces – Human-like voice applications are
quickly becoming the norm for customer service applications. Amazon Lex
can reduce the time and increase the quality of these chatbots.
● Query databases with a human-like language – Amazon Lex is combined
with other AWS database services to create sophisticated data analysis
applications with a human-like language interface.

23
 OUTPUT SCREENS

Fig 6: AWS Cloud 9

Fig 7: Seting up Relational DataBase

24
 Fig 8: Creating an auto scaling group

Fig 9: Importing data into RDS instances

25
 CONCLUSION:
I’ve also learned how to implement a machine learning pipeline. This included how to:

● Formulate a problem from a business request

● Obtain and secure data for machine learning

● Build a Jupyter notebook by using Amazon SageMaker

● Outline the process for evaluating data

● Explain why data needs to be preprocessed

● Use open-source tools to examine and preprocess data

● Use Amazon SageMaker to train and host a machine learning model

● Use cross-validation to test the performance of an ML model

● Use a hosted model for inference

● Create an Amazon SageMaker hyperparameter tuning job to optimize a model’s

effectiveness

26
What I have learned from this internship is how to use managed Amazon ML
services for forecasting, computer vision, and natural language processing, and I am
now able to:
● Describe the business problems that Amazon Forecast solves
● Describe the challenges of working with time series data
● List the steps that are required to forecast by using Amazon Forecast
● Use Amazon Forecast to make a prediction
● Describe the computer vision use cases
● Describe the managed Amazon ML services for image and video analysis
● List the steps that are required to prepare a custom dataset for object detection
● Describe how Amazon SageMaker Ground Truth can be used to prepare a custom
dataset
● Use Amazon Rekognition to perform facial detection
● Describe the natural language processing (NLP) use cases that are solved
by using managed Amazon ML services
● Describe the managed Amazon ML services available for NL

27
 REFERENCES:

1. https://aws.amazon.com/training/awsacademy/
2. https://docs.aws.amazon.com/
3. https://aws.amazon.com/
4. https://eduskillsfoundation.org/
5. https://en.wikipedia.org/wiki/Cloud_computing
6. https://www.geeksforgeeks.org/cloud-deployment-models/?ref=gcse
7. https://www.w3schools.in/cloud-computing
8. https://www.ibm.com/cloud/learn/cloud-computing#toc-cloud-comp-
noOVC-kh
9. https://www.redhat.com/en/topics/cloud-computing/what-are-cloud-
services

28