Scribd
Upload
9 views5 pages

AIML-Data Science - GenAI Course Syllabus

Uploaded by

sathyasubrahmanya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
9 views5 pages

AIML-Data Science - GenAI Course Syllabus

Uploaded by

sathyasubrahmanya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

DATA SCIENCE SYLLABUS

Essential Mathematics for data science:

Introduction

Introduction to data science and its application. what is data,types of Data, Legacy of Data mining,
Data science life cycle, steps involved in data science,Roles in Data Science,Use cases

Module 1:Probability Theory:

what is probability, sample space,Event,& Examples,Probability Measures,Probability Laws and


Rules: Addition Rule,Product Rule,Types for Probability:Marginal,conditional,joint probability,
conditional Probability and Bayes’ Theorem,Joint and Union Conditional , Introduction to
Probability Distributions for Data Science

Module 2:statistics for Data Science:

Introduction,Probability Versus Statistics, key terms,Populations, Samples, and Bias,Descriptive


statistics,Inferential Statistics, outliers & percentiles,Quartiles,Deviations,Mean Absolute
Deviation,Standard Deviation Variance,The T-Distribution,Binomial Distribution,Chi-Square
Distribution,Poisson and Related Distributions,Statistical Experiments and Significance
Testing:ANOVA,Chi-Square Test,

Module 3: Linear Algebra Foundation:

Matrices
Types of Matrices, Matrix Operations,Systems of Linear Equations & Inverse Matrices,Solving
Systems of Linear Equations

Vectors:
key concepts and Vector Operations,Vector Spaces,Span and Linear Dependence,Basis and Rank,
Linear Mappings:Linear Transformations:Basis Vectors,Matrix Vector Multiplication
Analytical Geometry:Norms,Inner Products,Lengths and Distances,Angles and Orthogonality and
other concepts

Module 4: Matrix Decomposition

Determinant and Trace,Eigen values and Eigenvectors,Cholesky


Decomposition,Eigendecomposition, Eigendecomposition of symmetric matrices
Eigendecomposition and Diagonalization,Singular Value Decomposition
LU decomposition, QR decomposition,

Advanced Mathematics
Module 5

Calculus

Graphs of functions,Limits and Derivatives & partial Derivatives,integrals, Advanced Integration


and Application,multivariate calculus->A gentle introduction, series & Taylor series, vector
calculus:vectors A revisit ,The Dot Product,Normal Equations of Planes,gradient vector,
maximum and minimum and chain rule,Lagrange Multipliers

Python Fundamentals
Module 1:Hello python:

what is Programming Language?,compiler, interpreter,Debuggers,IDE and Coding Environments


python introduction, variables ,keywords,Identifiers, data types in python,type conversion in
python,I/O and imports in python,Name spaces,flow controls in python

Module 2:functional Programming:

python functions, Buit-in functions,arguments and return types in python,Anonymous functions,


Global, local and non-local function,Global keyword in python,Introduction packages and modules
Data types in python:String,List,tuple,Dictionary,set,Frozen Set

Module 4: OOP Programming:

Class,Objects,Polymorphism,Encapsulation,Inheritance ,multiple inheritance,operator overloading


Data Abstraction

Module 4: Data structures in python

Byte array,Counters,Ordered-dict,Default-dict,Chain Map,Named Tuple,User Dict,User List,User-


string,Stack,Queue,Priority Queue,Linked List,
Deque,Heap queue,Binary Tree,Graph

Module 5:Advanced concepts:


file handling in python:opening file,writing to file, Errors and Exceptions,User Defined Exceptions,
Regular Expressions,Iterators,Generators,closures,Properties,Decorators in python,
Date and time functions,Map filter and Reduce functions in python,list comprehensions,Virtual
Environments and package installation using pip,
AI - ML

SUB TOPICS -01 MACHINE LEARNING(ML)

Module 1 :ML-Basics

Understanding data,types of data. Introduction to ML, Numpy & pandas with examples. Data
Science life cycle,types of Machine Learning:Supervised,Unsupervised,semi-
supervised,Reinforcement learning & more.(A basic introduction ).

Module 2: ML- Data Visualization & Algorithms:

Data visualization in python: introduction to matplotlib, seaborn & plotly,


Regression: types of regression,Linear Regression,Logistic Regression,Lasso Regression with
various examples
Gradient Descent (batch/stochastic/mini-batch) in Regression,
classification:binary classification , multi-class classification, F1-score,Accuracy,Roc
curve,decision tree classifier
Introduction to Naive Bayes:Bayes' Theorem,Text classification example
Finding neighbors: introduction to KNN: modeling and analysis on both regression and
classification
K-Means Algorithm in Unsupervised Learning and implementation.
Support vector machine learning:introduction ,types of svm, image classification using svm

Module 3:ML -Advanced

PCA: Principal Component Analysis-> finding principal components and modeling


Ensemble Learning:
------------------
Bagging,
Boosting: Gradient Boosting,ADA-BOOST,XGBOOST Algorithm->A detailed Analysis
stacking
time-series forecasting:
-------------------------
What is Time Series?, Trend, Seasonality, cyclical and random, Auto-regressive Model (AR),
Moving Average Model (MA), Stationarity of Time Series,ARIMA Model

SUB TOPICS -02 DEEP LEARNING (DL)


Module 3: DL- Basics

Introduction to neural networks,activation function, ,activation function, first neural


network,,introduction to feed Forward technique
and back-propagation, Gradient Descent Algorithm, Linear Regression/Logistic Regression Using
Neural network,

Module 4: DL- Dig deeper

Deep learning models:Introduction to CNN and RNN, working with TensorFlow and keras,cost and
loss functions in deep learning,
cost and loss functions in deep learning, working with MNIST Data,
optimzers in DNN -> A gentle introduction to Stochastic Gradient Descent Algorithm.
Generative Advertial Networks, A introduction to Generative AI(based on google certification
course)

SUB TOPICS -03 Artificial Intelligence (AI)

module 5: Computer Vision


---------------------------
Open-CV,opencv introduction and various image operation,computer vision concepts using open-
CV, introduction CNN with modeling , face detection using open-CV, emotion detection using
Neural network, a visit to YOLO model

Module 6: A Introduction to NLP:


Introduction to NLP,Text Preprocessing,Noise Removal,Lexicon Normalization, Object
Standardization,Text to Features (Feature Engineering on text data),Syntactical Parsing, Entity
Parsing,Statistical features,Word Embeddings,Important tasks of NLP,Text Classification and Text
Matching,Important NLP libraries
project : sentiment Analysis over twitter
Generative AI (Gen-AI)
Module 1:Advanced Gen-AI Concepts

Generative Adversarial Networks (GANs): Theory and Applications


• Encoders and AutoEncoders: Dimensionality Reduction and Feature Learning
• Variational AutoEncoders (VAE): Introduction to Latent Variables
• Attention Mechanisms: Introduction to Transformers, Multi-head Attention
• Transformers: Foundation for Large Language Models (LLMs)
• LLM Theory: Training Large Language Models, Pre-training, Fine-tuning

Module 2:Advanced Transformer Models

• BERT, GPT Models: Overview and Working Mechanisms


• RAG (Retrieval-Augmented Generation): Combining Retrieval and Generation for Task-
specific Applications
• RIG (Retrieval-Integrated Generation): Integrating Retrieval with Real-Time Generation
• Applications of RAG in Conversational AI, Chatbots, and Information Retrieval

You might also like