DATA SCIENCE

IIT CURRICULUM

1800-120-4748 www.teksacademy.com [email protected]

 Introduction to Data Science Overview
What is Data Science?
Why Data Science?
Where it is used?
Career Opportunities
About TEKS Academy
Learning Journey

Installation of Anaconda
Overview on Jupiter notebook

Module 01: Basic Python

Python Programming
Introduction to Python
Overview of Python and its features
Installing Python
Python IDEs
Writing and executing Python programs
Understanding Python's interactive mode and script mode

Python Basics
Python syntax and indentation
Python variables and data types (int, float, str, bool)
Input/output functions (input(), print())
Comments in Python

Data Structures in Python

Lists:
Creating and manipulating lists
List functions (append(), insert(), remove(), slicing)
Tuples:
Difference between lists and tuples
Accessing elements in a tuple

1800-120-4748 www.teksacademy.com [email protected]

 Sets:
Creating sets, set operations
union(), intersection(), difference()
Dictionaries:
Key-value pairs
Accessing and updating dictionaries
Common dictionary methods (get(), items(), keys(), values())

Control Structures
Conditional statements (if, elif, else)
Loops:
for loop
while loop
break, continue, and pass statements
Logical and comparison operators

Functions
Defining functions in Python
Function arguments and return values
Default and keyword arguments
*args and **kwargs
Lambda functions

Exception Handling
Errors in Python (syntax and runtime errors)
try, except, finally blocks
Raising exceptions using raise

Modules and Packages

Importing modules (import, from...import)
Standard Python libraries (math, random, os, sys, datetime)
Creating and using your own modules

1800-120-4748 www.teksacademy.com [email protected]

 File Handling
Reading from and writing to files (open(), read(), write())
Working with file modes (r, w, a, rb, wb)
Handling file exceptions

Object-Oriented Programming (OOPs) Basics

Introduction to classes and objects
Defining a class and object

Introduction to Python Libraries

Using Python libraries such as NumPy, Matplot and Pandas
Simple data analysis examples using these libraries

Module 02: Statistics and Probability

Introduction to Statistics
Definition and importance of statistics in data science
Types of data:
Numerical (Discrete and Continuous)
Categorical (Nominal and Ordinal)
Types of statistics:
Descriptive Statistics
Inferential Statistics
Population vs. Sample
Data Collection Techniques (Surveys, Experiments, Observations)

Descriptive Statistics
Measures of Central Tendency:
Mean, Median, Mode
Measures of Dispersion:
Range, Variance, Standard Deviation
Interquartile Range (IQR)
Shape of Data Distribution:
Skewness and Kurtosis

1800-120-4748 www.teksacademy.com [email protected]

 Data Visualization Techniques:
Bar charts, Histograms, Pie charts
Box plots, Scatter plots
Heatmaps

Probability Basics
Definition of Probability
Types of Probability:
Classical, Empirical, and Subjective Probability
Probability Rules:
Addition and Multiplication rules
Conditional Probability
Independent and Dependent Events
Bayes’ Theorem and Applications

Random Variables and Probability Distributions

Definition of Random Variables (Discrete and Continuous)
Probability Distribution of Random Variables
Expectation, Variance, and Standard Deviation of Random Variables
Cumulative Distribution Function (CDF)
Probability Density Function (PDF)

Sampling and Sampling Distributions

Importance of Sampling in Data Science
Types of Sampling Methods:
Simple Random Sampling
Stratified Sampling
Cluster Sampling
Systematic Sampling
Sampling Distribution of the Sample Mean
Central Limit Theorem (CLT)
Standard Error

1800-120-4748 www.teksacademy.com [email protected]

 Inferential Statistics
Point Estimation vs. Interval Estimation
Confidence Intervals for Means and Proportions
Hypothesis Testing:
Null and Alternative Hypotheses
Type I and Type II Errors
P-value and Significance Level
Z-test, T-test, and Chi-square test
ANOVA (Analysis of Variance)
Power of a Test

Correlation and Regression

Covariance and Correlation
Pearson Correlation Coefficient

Module 03: Data Cleaning with Pandas and Numpy

Introduction to Data Cleaning
Importance of Data Cleaning in Data Science
Common Data Quality Issues:
Missing Data
Duplicate Data
Incorrect Data Types
Inconsistent Data
Overview of Pandas and NumPy for Data Cleaning

Introduction to Pandas and NumPy

Installing and Setting Up Pandas and NumPy
Overview of Pandas DataFrames and Series
Overview of NumPy Arrays and Basic Operations
Importing Data using Pandas:
CSV, Excel, and JSON files
Data Inspection:
head(), info(), describe(), shape, and dtypes

1800-120-4748 www.teksacademy.com [email protected]

 Handling Missing Data
Identifying Missing Data:
isnull(), notnull(), isna(), sum()
Filling Missing Values:
Using fillna() and ffill(), bfill()
Filling with Mean, Median, Mode
Interpolation Techniques
Dropping Missing Values:
dropna() function and its parameters
Replacing Values using replace()

Handling Duplicate Data

Identifying Duplicate Rows:
duplicated(), drop_duplicates()
Removing Duplicate Rows and Columns
Dealing with Duplicate Values based on Conditions

Data Type Conversion

Checking Data Types with dtypes
Converting Data Types using astype():
Converting between integers, floats, and strings
Handling Date and Time Data with Pandas:
Converting to datetime using to_datetime()
Extracting date and time components (day, month, year, hour, minute)

Handling Inconsistent Data

String Manipulation:
Cleaning text data using str methods
Case conversion (lower(), upper())
Removing whitespace and special characters
Replacing substrings in text data
Dealing with Inconsistent Labels:
Renaming columns with rename()
Standardizing labels

1800-120-4748 www.teksacademy.com [email protected]

 Handling Outliers
Identifying Outliers:
Using statistical techniques (IQR, Z-score)
Visualizing outliers with Boxplots and Histograms
Treating Outliers:
Capping, Flooring, and Winsorization
Removing or transforming outliers

Data Transformation with Pandas

Applying Functions to Data using apply(), map(), and applymap()
Lambda Functions for Custom Operations
Creating New Columns from Existing Data
Grouping and Aggregating Data:
groupby(), aggregate(), transform()
Pivoting and Unpivoting Data with pivot(), melt()

Working with Large Datasets

Handling Large Data with NumPy:
Efficient data storage with NumPy arrays
Loading and Manipulating Large Files with Pandas:
Chunking large datasets
Memory optimization techniques (downcasting)
Using Dask for large-scale DataFrames

Merging and Joining DataFrames

Concatenating DataFrames with concat()
Merging DataFrames with merge():
Types of Joins (Inner, Outer, Left, Right)
Combining DataFrames using join()

Data Cleaning with NumPy

Introduction to NumPy Arrays for Data Cleaning
Element-wise Operations on Arrays

1800-120-4748 www.teksacademy.com [email protected]

 Handling Missing Values in NumPy:
np.nan, np.isnan(), and np.nan_to_num()
Using np.where() for Conditional Data Cleaning
Efficient Data Filtering using Boolean Indexing

Module 04: Normalization preprocessing using Scikit learn

Introduction to Data Normalization
Importance of Data Preprocessing in Data Science
Why Normalization is Needed:
Impact on Machine Learning Algorithms
Impact on Distance-Based Algorithms (KNN, K-means, etc.)
Difference between Normalization and Standardization
Overview of Scikit-learn Library

Overview of importing datasets using Scikit-learn and Seaborn

Introduction to Sklearn’s datasets module
Loading Data using Scikit-learn and Seaborn:
Datasets (Iris, Boston Housing, Penguins, titanic, etc..,)
Importing and converting data to Scikit-learn’s format
Data Inspection Techniques

Types of Normalization Techniques

Min-Max Scaling (Normalization):
Definition and Formula
Scaling values between 0 and 1
When to use Min-Max Scaling
Z-Score Standardization (Standard Scaling):
Definition and Formula
Mean and Standard Deviation-based scaling
When to use Standardization
MaxAbsScaler:
Scaling data by dividing by the maximum absolute value
Suitable for data that is already centered at 0

1800-120-4748 www.teksacademy.com [email protected]

 RobustScaler:
Scaling using the median and IQR to handle outliers
When to use RobustScaler

Data Transformation with Scikit-learn

Importing and Using MinMaxScaler
Importing and Using StandardScaler
Importing and Using MaxAbsScaler
Importing and Using RobustScaler
Applying Multiple Transformations using Pipeline

Applying Normalization to Different Data Types

Handling Numerical Features
Normalizing Categorical Data (One-Hot Encoding, Label Encoding)
Dealing with Mixed Data Types:
Custom Pipelines for Handling Heterogeneous Data

Normalizing and Standardizing Data with Scikit-learn

Using normalize() Function:
L1 and L2 Normalization Techniques
Data Preparation for Machine Learning Algorithms
Combining Normalization with Feature Engineering

Handling Outliers in Normalization

Effects of Outliers on Normalization Techniques
Scaling Data with Outliers using RobustScaler
Data Transformation using Log, Square Root, and Box-Cox Transformations

Feature Scaling for Machine Learning Models

Feature Scaling in Regression Algorithms
Normalization in Distance-Based Algorithms:
K-Nearest Neighbors (KNN)
K-Means Clustering

1800-120-4748 www.teksacademy.com [email protected]

 Importance of Scaling in Gradient-Based Algorithms:
Logistic Regression
Support Vector Machines (SVM)

Using Pipelines for Data Preprocessing

Overview of Scikit-learn Pipelines
Creating Custom Pipelines for Normalization and Preprocessing
Integrating Scaling and Normalization in Machine Learning Pipelines
Cross-validation with Preprocessing Pipelines

Dealing with Imbalanced Data

Handling Class Imbalances Before Normalization
Scaling Imbalanced Data:
Over-sampling and Under-sampling Techniques
Applying Normalization Post-Sampling

Data Normalization for Deep Learning

Normalization Techniques for Neural Networks
Batch Normalization
Importance of Scaling Inputs in Deep Learning

Module 05: Explorative Data Analysis with Visualization

Introduction to Exploratory Data Analysis (EDA)
Importance of EDA in Data Science
Goals of EDA: Detecting patterns, identifying anomalies, and hypothesis
formulation
Overview of Tools for EDA:
Pandas for data manipulation
Matplotlib, Seaborn, and Plotly for data visualization

Introduction to Data Visualization

Overview of Visualization Tools: Matplotlib, Seaborn, and Plotly
Basic Plot Types:
Line Plot, Bar Plot, Scatter Plot

1800-120-4748 www.teksacademy.com [email protected]

 Univariate Analysis with Matplotlib & Seaborn
Visualization of Single Variables
Numerical Data:
Histograms, Boxplots, Violin Plots
Categorical Data:
Bar Charts, Count Plots
Kernel Density Estimation (KDE) Plots

Bivariate Analysis with Matplotlib & Seaborn

Exploring Relationships between Two Variables
Scatter Plots for Numerical Data
Boxplots and Violin Plots for Categorical vs. Numerical Data

Multivariate Analysis with Matplotlib & Seaborn

Visualizing Multiple Variables
Pair Plots, Joint Plots, and Facet Grids
3D Scatter Plots and Bubble Charts
Correlation Matrices and Heatmaps

Customizing with Matplotlib

Customizing Plots: Titles, Labels, Legends, Grids
Subplots and Figure Layouts
Saving and Exporting Figures

Time Series Visualization

Line Plots for Time Series Data
Rolling Statistics and Moving Averages
Time Series Decomposition for Trend and Seasonality

1800-120-4748 www.teksacademy.com [email protected]

 Module 06: Machine Learning -Supervised Learning
Overview of Machine Learning

Introduction to Supervised Learning

Introduction to Supervised Learning
Difference between Supervised and Unsupervised Learning
Common Applications of Supervised Learning
Overview of Training and Testing Process:
Labels and Features, Train-Test Split

Data Preprocessing for Supervised Learning

Data Cleaning and Feature Scaling
Handling Missing Values
Encoding Categorical Data
Feature Engineering and Selection
Data Normalization and Standardization

Linear Regression
Introduction to Regression Problems
Simple Linear Regression
Multiple Linear Regression
Assumptions of Linear Regression
Evaluating Regression Models:
Mean Squared Error (MSE), Root Mean Squared Error (RMSE), R-Squared Value

Logistic Regression
Introduction to Classification Problems
Logistic Regression for Binary Classification
Sigmoid Function and Decision Boundaries
Evaluating Classification Models:
Confusion Matrix, Precision, Recall, F1-Score, ROC Curve, AUC

1800-120-4748 www.teksacademy.com [email protected]

 Decision Trees
Splitting Criteria: Gini Index, Entropy
Splitting Criteria: Gini Index, Entropy
Overfitting and Pruning Techniques
Pros and Cons of Decision Trees

Bagging and Random Forest

Introduction to Ensemble Learning
Working of Random Forest Algorithm
Feature Importance in Random Forest
Hyperparameter Tuning: Number of Trees, Max Depth

Support Vector Machines (SVM)

Introduction to Support Vector Machines
Linear and Non-linear SVM
Kernel Trick: Polynomial, RBF Kernel
Margin Maximization and Support Vectors
Hands-on: Handwritten Digit Classification

k-Nearest Neighbors (k-NN)

Introduction to k-NN Algorithm
Choosing the Optimal Value of k
Distance Metrics: Euclidean, Manhattan
Pros and Cons of k-NN
Hands-on: Classifying Iris Dataset

Naive Bayes Classifier

Introduction to Naive Bayes Algorithm
Types of Naive Bayes: Gaussian, Multinomial, Bernoulli
Assumptions and Applications of Naive Bayes
Hands-on: Spam Detection using Naive Bayes

1800-120-4748 www.teksacademy.com [email protected]

 Module 07: Ensemble Models
Introduction to Ensemble Learning
Overview of Ensemble Learning
Benefits of Ensemble Methods:
Reducing Overfitting
Improving Prediction Accuracy
Types of Ensemble Learning:
Bagging, Boosting, Stacking

Bagging Techniques
Introduction to Bagging:
Definition and Concept
How Bagging Reduces Variance
Decision Tree Ensembles:
Random Forest Algorithm
Building and Tuning Random Forest Models
Out-of-Bag Error Estimation

Boosting Techniques
Introduction to Boosting:
Definition and Concept
How Boosting Reduces Bias
Common Boosting Algorithms:
AdaBoost
Gradient Boosting Machines (GBM)
XGBoost: Features and Implementation
LightGBM and CatBoost: Differences and Use Cases

Stacking and Blending

Introduction to Stacking:
Definition and Concept
Combining Multiple Models

1800-120-4748 www.teksacademy.com [email protected]

 Building a Stacked Model:
Choosing Base Learners
Using a Meta-learner
Practical Implementation of Stacking

Module 08: Machine Learning – Unsupervised

Introduction to Unsupervised Learning
Overview of Unsupervised Learning
Difference Between Supervised and Unsupervised Learning
Applications of Unsupervised Learning
Overview of Clustering and Dimensionality Reduction

k-Means Clustering
Introduction to Clustering
Working of k-Means Algorithm
Evaluating Clusters:
Elbow Method to Find Optimal Number of Clusters
Silhouette Score

Hierarchical Clustering
Introduction to Hierarchical Clustering
Agglomerative vs. Divisive Clustering
Dendrograms and Linkage Methods
Pros and Cons of Hierarchical Clustering

DBSCAN (Density-Based Spatial Clustering)

Introduction to DBSCAN Algorithm
Concept of Density Reachability and Density Connectivity
Identifying Outliers and Noise in DBSCAN
Choosing Parameters: Epsilon, MinPts

1800-120-4748 www.teksacademy.com [email protected]

 Principal Component Analysis (PCA)
Introduction to Dimensionality Reduction
Working of PCA Algorithm
Eigenvalues and Eigenvectors in PCA
Explained Variance and Choosing Number of Components
Visualizing PCA for High-Dimensional Data

t-SNE (t-Distributed Stochastic Neighbor Embedding)

Introduction to t-SNE for Non-linear Dimensionality Reduction
Visualizing High-Dimensional Data in 2D/3D
Differences between PCA and t-SNE

Association Rule Learning (Apriori Algorithm)

Introduction to Market Basket Analysis
Support, Confidence, and Lift
Apriori Algorithm for Finding Association Rules
Applications of Association Rules in Retail and E-commerce

Anomaly Detection
Introduction to Anomaly Detection
Techniques for Identifying Outliers
Isolation Forest, One-Class SVM
Applications of Anomaly Detection in Fraud Detection and Network Security

Module 09: Time Series Analysis

Introduction to Time Series Analysis
Characteristics of Time Series Data
Components of Time Series:
Trend, Seasonality, Noise
Importance of Time Series Analysis in Data Science

1800-120-4748 www.teksacademy.com [email protected]

 Time Series Decomposition
Decomposing Time Series into Components
Seasonal and Trend Decomposition using STL (Seasonal-Trend decomposition
using Loess)
Visualizing Decomposed Components

Time Series Forecasting Methods

Introduction to AR & MA Models :
AR Model
MA Model
ARMA Model
ARIMA Model

Evaluating Time Series Models

Metrics for Time Series Forecasting:
MAE, MSE, RMSE, MAPE
Train-Test Split for Time Series Data
Walk-Forward Validation

Module 10: Deep Learning

Introduction to Deep Learning
Overview of Artificial Intelligence, Machine Learning, and Deep Learning
Historical Context and Evolution of Deep Learning
Key Differences between Traditional ML and Deep Learning
Applications of Deep Learning in Data Science

Foundations of Neural Networks

Introduction to Neurons and Perceptrons
Structure of a Neural Network
Activation Functions: Sigmoid, ReLU, eLU, Leaky ReLU, Tanh, Softmax, Softplus
Forward Propagation and Loss Calculation
Understanding Cost Functions

1800-120-4748 www.teksacademy.com [email protected]

 Training Neural Networks
Backpropagation Algorithm
Gradient Descent and its Variants:
Stochastic Gradient Descent (SGD)
Adam, RMSprop
Learning Rate and its Importance
Overfitting and Underfitting
Techniques to Prevent Overfitting: Regularization, Dropout

Deep Neural Networks (DNNs)

Constructing Deep Neural Networks
Importance of Depth and Width in Networks
Vanishing and Exploding Gradients Problem
Batch Normalization

Practical Implementation with TensorFlow and Keras

Setting Up the Environment for TensorFlow
Building and Training Models using Keras
Handling Datasets with TensorFlow Datasets (TFDS)
Model Evaluation and Metrics: Accuracy, Precision, Recall, F1-score
Saving and Loading Models

Practical Implementation with PyTorch

Setting Up the Environment for PyTorch
Building Neural Networks with PyTorch
Data Handling and Augmentation in PyTorch
Model Training and Evaluation in PyTorch
Using Pretrained Models in PyTorch

1800-120-4748 www.teksacademy.com [email protected]

 Module 11: Natural Language Processing (NLP) with NLTK
Introduction
Text Preprocessing Techniques
Stemming, Limitation, Stop words,
TFIDE, Word2 vec
Word Embedding
Word Cloud.

Deployment using Streamlit

Module 12: SQL Data Base

Introduction to SQL
History and evolution of SQL
SQL vs NoSQL
Types of databases (RDBMS, column-based, key-value, etc.)
Database concepts: Tables, Rows, Columns, Relationships

SQL Data Types

Numeric types (INT, FLOAT, DECIMAL)
Character types (CHAR, VARCHAR, TEXT)
Date and time types (DATE, TIME, TIMESTAMP)
Boolean types
BLOB (Binary Large Object)

Database Design
Normalization (1NF, 2NF, 3NF, BCNF)
Denormalization
Primary keys, foreign keys, and unique keys
Indexing
Constraints (NOT NULL, DEFAULT, UNIQUE, CHECK)

1800-120-4748 www.teksacademy.com [email protected]

 Basic SQL Queries
SELECT statement
WHERE clause and logical operators (AND, OR, NOT)
ORDER BY clause
LIMIT and OFFSET clauses
DISTINCT keyword

SQL Functions
Aggregate functions (COUNT, SUM, AVG, MIN, MAX)
Scalar functions (UPPER, LOWER, LENGTH, ROUND)
Date functions (NOW, CURDATE, DATE_ADD, DATE_SUB)

Joins in SQL
INNER JOIN
LEFT JOIN (or LEFT OUTER JOIN)
RIGHT JOIN (or RIGHT OUTER JOIN)
FULL OUTER JOIN
CROSS JOIN
Self joins

Subqueries and Nested Queries

Single-row subqueries
Multi-row subqueries
Correlated subqueries
EXISTS and NOT EXISTS clauses

Set Operations
UNION and UNION ALL
INTERSECT
EXCEPT (or MINUS)

1800-120-4748 www.teksacademy.com [email protected]

 Data Manipulation Language (DML)
INSERT statement
UPDATE statement
ADD statement
DELETE statement
TRUNCATE statement

Data Definition Language (DDL)

CREATE TABLE
ALTER TABLE (add, modify, drop columns)
DROP TABLE
CREATE VIEW, DROP VIEW

Constraints in SQL
PRIMARY KEY constraint
FOREIGN KEY constraint
UNIQUE constraint
CHECK constraint
DEFAULT constraint

Transactions in SQL
ACID properties (Atomicity, Consistency, Isolation, Durability)
COMMIT and ROLLBACK
SAVEPOINT
Transaction isolation levels (READ UNCOMMITTED, READ
COMMITTED, REPEATABLE READ, SERIALIZABLE)

Indexes in SQL
Purpose of indexes
Types of indexes (single-column, multi-column)
Unique and non-unique indexes
Full-text index
Index performance considerations

1800-120-4748 www.teksacademy.com [email protected]

 SQL Views
Creating views
Updating views
Dropping views
Advantages and limitations of views
SQL Trigger

Stored Procedures and Functions

Creating stored procedures
IN, OUT, and INOUT parameters
Creating user-defined functions
Differences between stored procedures and functions

Module 13: Power BI

Introduction to Power BI
Overview of Business Intelligence and Data Visualization
Importance of Power BI in Data Science
Components of Power BI:
Power BI Desktop, Power BI Service, Power BI Mobile
Installation and Setup of Power BI Desktop

Getting Started with Power BI Desktop

Interface Overview: Ribbon, Fields Pane, Visualizations Pane
Importing Data:
Connecting to various data sources (Excel, SQL, Web, etc.)
Understanding Data Types and Basic Data Profiling

Data Transformation with Power Query

Introduction to Power Query Editor
Data Cleaning Techniques:
Removing duplicates, filtering rows, and changing data types
Merging and Appending Queries
Creating Custom Columns and Calculated Fields
Handling Missing Values

1800-120-4748 www.teksacademy.com [email protected]

 Data Modeling in Power BI
Understanding Relationships: One-to-One, One-to-Many, Many-to-Many
Creating and Managing Relationships between Tables
Using Star Schema and Snowflake Schema for Data Models
Introduction to Data Hierarchies

DAX (Data Analysis Expressions) Basics

Introduction to DAX: What It Is and Why It’s Important
Creating Calculated Columns and Measures
Basic DAX Functions:
SUM, AVERAGE, COUNT, DISTINCTCOUN
Time Intelligence Functions:
YTD, QTD, MTD calculations

Data Visualization Techniques

Creating Basic Visualizations:
Stacked Column charts, Line charts, Pie charts,Donut Chart, Ribbon Plot,
Tables, and Matrix
Advanced Visualizations:
Treemaps, Waterfall charts, Scatter plots, Maps
Custom Visualizations from Power BI Marketplace
Best Practices for Data Visualization Design

Creating Interactive Reports and Dashboards

Designing Interactive Reports:
Using slicers, filters, and drill-through functionality
Creating Bookmarks and Buttons for Navigation
Tips for Effective Dashboard Design
Publishing Reports to Power BI Service

1800-120-4748 www.teksacademy.com [email protected]

 Module 14: Data Summarization, Charts & Formatting
Getting data from CSV files, databases, workbooks, webpages
Max, Min with IF and IFS, CountlFS
Sum, Product, Sumproduct, Average, Standard Deviation, Variance
LOOKUP,VLOOKUP, HLOOKUP
Various types of Charts – pie chart, Column chart, line chart, Scatter Plot
Changing Font, Data Type of column, Conditional Formatting, Format painter
Alignment Techniques – Merging and Wrapping
Data Summarization: Pivot Table
Cleaning data, extracting data from multiple sources
Filters, Sorting, Concatenation, Merging

1800-120-4748 www.teksacademy.com [email protected]

 Additional IIT Guwahati Curriculum

Data Engineering, Cloud Integration (AWS) & Gen AI

Module 01: Introduction to Gen AI

Introduction to AI
AI vs ML vs DL
Types of learning (Supervised, Unsupervised & Reinforcement)
Core Difference between ML and DL
Life Cycle of ML and DL Project
Introduction to Generative AI
Overview of generative AI technologies.
Applications and case studies across industries

Module 02: Advanced NLP and Embeddings

Word Embeddings:
Word2Vec: Skip-Gram, CBOW
GloVe: Global Vectors for Word Representation
Sequence Models:
RNNs, LSTMs, GANs
Attention Mechanisms
Applications:
Machine Translation
Text Summarization

Module 03: Transformers and LLMs

Transformers Basics:
Self-Attention Mechanism
Encoder-Decoder Architecture

1800-120-4748 www.teksacademy.com [email protected]

 Popular LLMs:
BERT: Fine-Tuning for Text Classification, NER
GPT: Text Generation, Dialogue Systems
Hugging Face Ecosystem:
Pretrained Models
Tokenizers and Datasets

Module 04: Prompt Engineering

Basics of Prompt Engineering:
Prompt Design: Direct and Chain-of-Thought Prompts
Few-Shot, Zero-Shot Learning
Fine-Tuning LLMs:
Domain-Specific Tuning
Case Studies: Medical, Financial NLP

Module 05: Gen AI Applications

Introduction to LangChain
Introduction to Vector Database
ChromaDB, Pinecone
Build a Simple LLM Application
Build a Chatbot LLM Application

Module 06: Practical Implementation of Gen AI

Building Chatbot With Message History Using Langchain
Building Conversational Q&A Chatbot With Message History
End To End Search Engine GEN AI App using Tools And Agent With Open Source
LLM

1800-120-4748 www.teksacademy.com [email protected]