WEE
K
ACTIVITY LOG FOR THE FIRST
Day Person
& Learning Outcome InCharge
Date Brief description of the Signature
daily activity
Foundations
around
Introduction to AWS AWS Academy
Day – 1
Academy Machine Machine Learning
Learning Foundations Foundations.
Day - 2 Finding out what to
expect from AWS
Course Introduction
Academy Machine
Video
Learning
Foundations.
Day – 3
Module - 2
Introducing
Course Prerequisites
Machine Learning.
and Objectives
Day – 4 Implementing a ML
Pipeline with
Module - 3 & 4 Amazon
Course Prerequisites SageMaker
and Objectives &
Introducing
Forecasting.
Introducing
Day – 5 Module - 5 & 6 Computer Vision
Course Prerequisites &
and Objectives Introducing NLP.
Summary of the key
concepts and skills
Day – 6 we'll learn.
Course Summary
W
F
WEE
K
r
Objective of the Activity Done:
To know about the Introduction to
AWS Academy Machine Learning
Foundations, Course Introduction
Video, Module - 2,3,4,5,6 Course
Prerequisites and Objectives, Course
Summary.
Detailed Report:
Introducing Machine Learning:
In this section, you can expect to gain
an understanding of the fundamental
concepts of machine learning,
including supervised learning,
unsupervised learning, and
reinforcement learning.
Implementing an ML Pipeline with
Amazon SageMaker:
This part of the program will likely
focus on using AWS SageMaker, a fully
managed machine learning service, to
build, train, and deploy machine
learning models.
You can expect to learn how
to use SageMaker for
data preparation, model
selection, and
hyperparameter tuning.
Introducing Forecasting:
This section should introduce you to
time series forecasting, one of the
important applications of machine
learning.
You can expect to learn about the
challenges and techniques associated
with forecasting, including methods
WEE
K
for working with time series data and
predictive modeling.
Introducing Computer Vision:
In this segment, you will explore
computer vision, which involves the
analysis and understanding of images
and videos.
You can expect to learn about image
processing techniques, object
detection, image classification, and the
use of AWS services for computer
vision tasks.
Introducing NLP (Natural Language
Processing):
In the NLP portion, you will delve into
the field of natural language
processing, focusing on the interaction
between computers and human
language.
ACTIVITY LOG FOR THE SECOND
Person In-
Day &
Charge
Date Brief description of the
Signature
daily activity Learning Outcome
Day – 1 What Is Machine Learning?
The result or
prediction generated
by a machine learning
model.
Day - 2
Has the potential to
address a wide range
of business problems
Business Problems Solved With across various
Machine Learning industries.
Day – 3 Machine Learning
Process Involves several
stages, from data
collection and
preparation to model
development.
Day – 4 Machine Learning Tools Play a crucial role in
Overview various
industries,
from
healthcare to
finance.
Day – 5 Machine Learning
Challenges Ability to extract
insights, make
predictions, and
automate tasks from
large datasets.
Process used to gauge
someone's
understanding or
knowledge about a
Day – 6 Knowledge Check particular topic.
W
O
WEE
K
R
/
2
Objective of the Activity Done:
To know about What Is Machine
Learning?, Business Problems Solved
With Machine Learning,
Machine Learning Process, Machine
Learning Tools Overview, Machine
Learning Challenges.
Detailed Report:
Machine learning is a subset of
artificial intelligence (AI) that focuses
on the development of algorithms and
models that enable computers to learn
and make predictions or decisions
based on data, without being explicitly
programmed. It's a way for computers
to recognize patterns, make sense of
data, and improve their performance
over time. Machine learning can be
categorized into three main types:
supervised learning, unsupervised
learning, and reinforcement learning.
Machine learning can be
applied to a wide range of
business problems,
including: Customer
Churn Prediction:
Predicting which
customers are likely to
churn or cancel their
subscriptions, allowing
businesses to take
proactive retention
actions.
WEE
K
Credit Risk Assessment: Assessing the
creditworthiness of loan applicants by
analyzing their financial history and
other data.
The machine learning process typically
involves the following steps:
Problem Definition: Define the
problem you want to solve and the
objectives you aim to achieve with
machine learning.
Data Collection: Gather relevant data,
which may include structured data
from databases and unstructured data
from various sources.
Machine learning is a rapidly evolving
field with a wide range of tools and
frameworks that enable developers
and data scientists to build, train, and
deploy machine learning models:
Python: Python is the most popular
programming language for machine
learning. It offers a wide range of
libraries and frameworks, such as
NumPy, Pandas, and scikit-learn, that
are essential for data manipulation,
preprocessing, and modeling.
TensorFlow: Developed by Google,
TensorFlow is an open-source machine
learning framework that provides a
comprehensive ecosystem for
developing deep learning models.
Machine Learning Challenges:
Data Quality: High-quality data is
essential for training accurate machine
learning models. Challenges include
missing data, noisy data, and data
biases.
Overfitting and Underfitting:
Balancing model complexity to avoid
underfitting (model is too simple) or
overfitting (model fits the training data
too closely) is a common challenge.
Interpretable Models: Many machine
learning algorithms, especially deep
learning models, are often considered
black boxes, making it difficult to
interpret their decision-making
processes.
ACTIVITY LOG FOR THE THIRD
Person In- Charge
Day Signature
Brief description of the
& Learning Outcome
daily activity
Date
Day – 1
Is a crucial step in
the development
Formulating Machine of machine
Learning Problems learning systems.
Day - 2 Collecting & Securing Data
Is a crucial aspect of
any data-driven
initiative, business
analytics, machine
learning.
Day – 3 Evaluating Your Data
Is a critical step in the
process of working
with data, preparing it
for machine learning
or data analysis.
Transform existing
Day – 4 Feature Engineering ones to improve the
performance of your
models.
WEE
K
Is a critical step in
Day – 5 deploying it for
Hosting & Using The practical applications.
Model
Day – 6 Evaluating The Accuracy Is a crucial step in
Of The Model assessing its
performance and
determining how well
it can make
predictions on new,
unseen data.
W
E
E
K
L
Y
R
E
P
O
R
T
W
E
E
K
-
3
(
F
r
o
m
D
t
:
/
/
2
3
t
o
D
t
:
/
/
2
3
)
Objective of the Activity Done:
To know about Formulating
Machine Learning Problems,
Collecting & Securing Data, Evaluating
Your Data, Feature Engineering,
Hosting & Using The Model,
Evaluating The Accuracy Of The
Model.
Detailed Report:
Formulating Machine Learning
Problems:
Define the problem you want to solve
and determine whether it's a
classification, regression, clustering, or
other type of problem.
Specify the goals and objectives of the
machine learning project, including
what you want to achieve with the
model.
Collecting & Securing Data:
Identify the data sources where you
can obtain relevant data for your
problem.
WEE
K
Collect and gather the necessary data,
which can include structured and
unstructured data from various
sources.
Evaluating Your Data:
Conduct data exploration to
understand the characteristics of your
data, such as data distributions,
missing values, outliers, and potential
data quality issues.
Perform data preprocessing tasks, such
as data cleaning, normalization, and
handling missing values.
Feature Engineering:
Feature engineering involves selecting,
transforming, or creating features from
the raw data to improve the model's
performance.
Techniques may include one-hot
encoding, feature scaling, feature
selection, and creating interaction
terms.
Hosting & Using The Model:
Once the model is trained and
evaluated, deploy it to a production
environment or cloud platform.
Create APIs or endpoints for making
predictions using the model.
Ensure that the model can handle
incoming data and provide predictions
in real-time.
Evaluating The Accuracy Of The
Model:
Use relevant evaluation metrics, such
as accuracy, precision, recall, F1-score,
ROC-AUC, MAE, or RMSE, depending
on the problem type.
Compare the model's performance to a
baseline model and assess how well it
meets the project's objectives.
ACTIVITY LOG FOR THE FORTH
Person In-
Day Charge
& Learning Outcome Signature
Date Brief description of the
daily activity
Process of
making
Day – 1 Forecasting Overview predictions about
future events.
Involves preparing and
transforming temporal
Day - 2 data for analysis and
Processing Time Series modeling.
Data
Day – 3 Special Considerations For
Time Series Data
Presents unique
challenges and
considerations in the
context of machine
learning.
Day – 4 Using Amazon Forecast
Enables to build
accurate forecasting
models for various
business use cases.
Day – 5 Creating A Forecast With Can be used for a
Amazon Forecast wide range of
applications, from
demand forecasting
to financial planning.
WEE
K
Day – 6 Knowledge Check Process used to gauge
someone's
understanding or
knowledge about a
particular topic
W
E
E
K
L
Y
R
E
P
O
R
T
W
E
E
K
-
4
(
F
r
o
m
D
t
:
/
/
2
3
t
o
D
t
:
/
/
2
3
)
Objective of the Activity Done:
To know about the Forecasting
Overview, Processing Time Series
Data, Special Considerations
For Time Series Data, Using Amazon
Forecast, Creating A Forecast With
Amazon Forecast.
Detailed Report:
Forecasting Overview:
Forecasting is the process of making
predictions or estimates about future
events or trends based on historical
data and patterns. Time series
forecasting, a specific type of
forecasting, focuses on predicting
future values of a variable based on its
historical values at different time
intervals. It has numerous
applications, such as demand
forecasting, financial forecasting,
weather forecasting, and more.
Processing Time Series Data:
Data Collection: Gather historical time
series data, including timestamps and
target variables. Ensure data is
accurate and relevant to the forecasting
problem.
Data Preprocessing:
Handle missing data: Impute or
interpolate missing values if necessary.
Handle outliers: Identify and deal with
outliers that can distort forecasts.
WEE
K
Special Considerations For Time Series
Data:
Seasonality: Many time series exhibit
seasonal patterns, and models need to
capture and adjust for this. Trends:
Identifying and modeling trends is
crucial, as time series data often has
upward or downward trends.
Using Amazon Forecast:
Amazon Forecast is a managed
machine learning service specifically
designed for time series forecasting. It
streamlines the process of creating
accurate forecasts. Here's how you can
use Amazon Forecast:
Data Preparation:
Upload your historical time series data
to Amazon Forecast using the AWS
Management Console, SDKs, or APIs.
Creating A Forecast With Amazon
Forecast:
Data Preparation:
Ensure you have your historical time
series data ready in a suitable format.
Amazon Forecast Setup:
Sign in to the AWS Management
Console and access Amazon Forecast.
Dataset Group and Dataset Creation:
Create a dataset group and specify the
schema for your data.
ACTIVITY LOG FOR THE FIFTH
Person In-
Day Charge
& Learning Outcome Signature
Date Brief description of the daily
activity
Day – 1 Introduction To
It focuses on enabling
Computer Vision
machines, typically
computers, to
interpret, understand,
and process visual
information from the
world.
Image And Video Analysis
These tasks have a
Day - 2 wide range of
applications across
various industries.
It has significant
Day – 3 Facial Recognition attention
and applications in
various domains.
Is a crucial step in
Day – 4 developing accurate
Preparing Custom Datasets machine learning
For Computer Vision models.
The training dataset is
used to teach the
Day – 5 model the
relationships.
Creating The Training
Dataset
Day – 6 Creating The Test The test dataset is
Dataset used to assess the
model's performance
on unseen data,
which helps gauge
its ability to
generalize.
WEEKLY REPORT WEEK-5
(From Dt: / /23 to Dt: / /23 )
Objective of the Activity Done:
To know about the Introduction To Computer Vision, Image And Video Analysis, Facial Recognition,
Preparing Custom Datasets For Computer Vision, Creating The Training Dataset, Creating The Test
Dataset.
Detailed Report:
Introduction to Computer Vision:
Computer vision is a field of artificial intelligence that focuses on enabling computers to interpret,
understand, and make decisions based on visual data from the world. It involves developing algorithms
and models to process and analyze images and videos, enabling applications and more.
Image and Video Analysis:
Image and video analysis are fundamental tasks in computer vision. They involve extracting meaningful
information from images and videos, including identifying objects, tracking movement, recognizing
patterns, and more.
Facial Recognition:
Facial recognition is a specific application of computer vision that involves identifying and verifying
individuals based on their facial features. It has various uses, including unlocking smartphones, security
systems, and access control. Facial recognition algorithms analyze unique facial characteristics, such as
the distances between eyes, nose, and mouth, to match faces against a database.
Preparing Custom Datasets for Computer Vision: Data
Collection:
Collect images or videos relevant to your task. This could involve capturing new data or obtaining
existing data from various sources.
Creating the Training Dataset:
Data Split:
If your dataset isn't already split, divide it into training, validation, and test sets. The training dataset is
used to train the model.
Creating the Test Dataset:
Data Split:
Reserve a portion of your data for testing. It should be distinct from the data used for training and
validation.
ACTIVITY LOG FOR THE SIXTH WEEK
Person In- Charge
Signature
Learning Outcome
Brief description of the daily
activity
Understood the
validation of the process
Overview Of Natural
Language Processing
Understood how to
follow our Path to Value
Natural Language Processing to deliver business
Managed Services value.
Amazon Comprehend
Understood exchange
with other
participants
Learnt the basics of EMS
Platform Technologies
Amazon Polly
Amazon Translate
Learnt to set up and
use Celonis' Task
Mining Service with
Quickstarts.
Learnt about adding
Knowledge Check value to organization
through automating
business processes
WEEKLY REPORT WEEK-6
(From Dt: / /23 to Dt: / /23)
Objective of the Activity Done:
To know about the Overview Of Natural Language Processing, Natural Language Processing
Managed Services, Amazon Comprehend, Amazon Polly, Amazon Translate.
Detailed Report:
Natural Language Processing (NLP) Overview:
NLP aims to enable computers to understand and generate human language, facilitating tasks
like text analysis, chatbots, sentiment analysis, and more.
Core NLP tasks include tokenization, part-of-speech tagging, syntactic parsing, named entity
recognition, and semantic analysis.
NLP leverages machine learning techniques, including deep learning models like Transformers,
to improve language understanding.
Natural Language Processing Managed Services:
Managed NLP services offer pre-built tools and models, reducing the need for custom
development. AWS provides several services for NLP tasks.
Amazon Comprehend:
Amazon Comprehend is an NLP service that offers a range of capabilities, including sentiment
analysis, entity recognition, language detection, keyphrase extraction, and
document classification.
It supports multiple languages and can be used for tasks like content categorization, brand
monitoring, and customer feedback analysis.
Amazon Polly:
Amazon Polly is a text-to-speech (TTS) service. It converts text into lifelike speech using advanced
deep learning technologies.
Polly can generate speech in various languages and voices, making it useful for voice assistants,
audiobooks, and other applications that require spoken content.
Amazon Translate:
Amazon Translate is an automatic translation service that can translate text between different
languages.
It supports a wide range of languages and is useful for translating website content, customer
support interactions, and other multilingual applications.
