0% found this document useful (0 votes)
4 views8 pages

Full Stack AI Data Science

The document outlines a comprehensive course on Python programming, data science, machine learning, and deep learning, emphasizing practical applications and real-world problem-solving. It includes modules on data analysis, regression algorithms, classification techniques, model evaluation, and deployment using FastAPI, along with hands-on projects. The course is designed for individuals looking to build a career in AI and data science, providing essential tools and resources for success.

Uploaded by

listbook477
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
0% found this document useful (0 votes)
4 views8 pages

Full Stack AI Data Science

The document outlines a comprehensive course on Python programming, data science, machine learning, and deep learning, emphasizing practical applications and real-world problem-solving. It includes modules on data analysis, regression algorithms, classification techniques, model evaluation, and deployment using FastAPI, along with hands-on projects. The course is designed for individuals looking to build a career in AI and data science, providing essential tools and resources for success.

Uploaded by

listbook477
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

এই ক োর্টি

স শূন্য কেক শুরু কে এ জন্ শশক্ষোেীক ধোকে ধোকে Python করোগ্রোশ িং (basic, data
structure, OOP) কশখোকে, যোকে কর্ real কেিো শন্কে োজ েকে েোকে। এেেে Machine
Learning ও Deep Learning–এে গুরুত্বেূর্ স অ্যোলগশেদ েযেহোে কে real-life problem
র্ োধোকন্ে দক্ষেো অ্জসন্ েকে। েোশোেোশশ FastAPI েযেহোে কে ML কেলক API আ োকে
শেপ্লে েো, কেিো শিশন্িং, শিচোে ইঞ্জিশন্েোশেিং ও কেল ইভোলুকেশন্র্হ র্ম্পূর্ সend-to-end Full
Stack AI & Data Science রকজক্ট তেশে েোে েোস্তে অ্শভজ্ঞেো অ্জসন্ েকে।

–---------------------------------------
Instructor:
Kawchar Husain
LinkedIn | Kaggle | GitHub | CodeForces

[Link]
Module 01: Introduction to Data Science & AI
Class 01: Intro

● Data Science overview


● AI vs ML vs Deep Learning
● Supervised vs Unsupervised Learning
● Regression, Classification, Clustering
● Real-world use cases
● Career paths for ML/AI domain (ML+Analytics vs. Academic vs. ML+SWE)
● Required tools
● Required platforms (GitHub, Kaggle, Colab)
● Additional materials on Linear Algebra and Statistics
● Q&A Session

Module 02: Python for Data Science


Class 02: Python Basics

● Setting up the IDE


● Python syntax
● Variables & data types
● Conditions
● Loops
● Break, Continue, Pass Statements
● Functions (def, return, parameters)
● Basic problem solving

Assignment: Python problems

Class 03: Data Structures

● List
● Tuple
● Set
● Dictionary
● When & why to use each
● Hands-on practice

Assignment: Python problems

[Link]
Class 04: OOP & Exception Handling

● Class & object


● Constructor (__init__)
● Methods & attributes
● Inheritance & encapsulation
● Exception handling (try/except)
● Writing reusable ML-ready code

Assignment: Python problems

Module 03: Data Analysis & Preprocessing


Class 05: Data Understanding & Cleaning

● Different kinds of data types


● Raw data preprocessing
● Missing value handling techniques
● Outlier handling (practical rules)
● EDA using Pandas
● Visualization with Matplotlib, Seaborn, and Plotly
● Implementation with Python

Class 06: Data Transformation

● Encoding categorical variables


● Scaling & Normalization techniques
● Imbalanced data handling: SMOTE, SMOTETomek & Class weights
● Train, Test, Validation
● Preventing data leakage
● Implementation with Python

Assignment: Data Cleaning and Transformation

Module 04: Regression Algorithms


Class 07: Simple and Multiple Variable Regression

● Regression intuition
● Linear Regression
● Loss functions (conceptual)
● Regression metrics

[Link]
● R² score
● Python sklearn implementation

Class 08: Polynomial Regression & Regularization Techniques

● Why polynomial over a linear


● Polynomial regression intuition
● Overfitting vs underfitting
● Lasso & Ridge (usage-focused)
● Feature impact understanding
● Implementation with Python

Class 09: KNN and Deployment Basics

● Distance-based regression
● Choosing K
● KNN for regression and classification
● ML Pipeline
● Introduction to Gradio

Project: House Price Predictor with Web UI and Deployment

Module 05: Classification Algorithms


Class 10: Logistic Regression

● Binary & multiclass classification


● Decision boundary intuition
● Implementation
● Confusion matrix
● Accuracy, precision, recall, F1
● ROC & AUC
● Implementation with Python

Assignment: Model Evaluation

Class 11: Support Vector Machine (SVM) & Cross Validation

● Margin & hyperplane intuition


● Kernel idea (visual)
● Implementation with Python
● K-Fold & Stratified K-Fold CV

[Link]
Class 12: Naive Bayes & NLP Fundamentals

● Basic probability
● Bayes theorem
● Naive Bayes (practical probability)
● Text Preprocessing & Vectorization

Project: End-to-end Fake News Classifier App

Assignment: End-to-end Amazon Product Review Analysis App

Class 13: Decision Tree & Ensemble Learning

● Decision Tree intuition


● Bagging vs. Boosting
● Gradient Boosting
● Random Forest
● XGBoost
● CatBoost
● Implementation with Python

Assignment: Find wine quality using decision tree, random forest, XGBoost

Module 06: Model Evaluation & Optimization


Class 14: Hyperparameter Tuning & Project

● Grid Search
● Random Search
● Bayesian Optimization (conceptual)
● Automated tuning (Optuna)

Assignment: Search optimal parameters for the XGBoost model from class 13.

Module 07: Unsupervised Learning


Class 15: Cluster Analysis

● Unsupervised learning concepts


● K-Means clustering
● Elbow method

[Link]
Project: End-to-End Cluster Analysis App with Streamlit

Assignment: Customer segmentation

Module 08: Time Series Analysis


Class 16: Time Series for Machine Learning

● Time-series basics
● Stationary vs non-stationary
● ARIMA & SARIMA
● Prophet

Project: Stock Market Forecast

Module 09: Model Deployment with FastAPI


Class 17: FastAPI for AI/ML
● What is FastAPI
● Importance of FastAPI for ML
● REST API basics (GET, POST)
● Creating an ML inference API
● Request/response schema with Pydantic
● Model loading & prediction endpoint
● Testing API with Swagger UI
● Basic deployment readiness
● Additional resource on FastAPI

Project: ML Model Inference API using FastAPI

Module 10: Deep Learning with PyTorch


Class 18: Neural Network Foundations

● Neuron
● Perceptron
● ANN
● Activation functions
● Loss functions
● Training workflow
● Optimizers

[Link]
Class 19: PyTorch Fundamentals

● Tensors
● Dataset & DataLoader
● Training & evaluation loop
● Implementing ANN with PyTorch

Class 20: Computer Vision with CNN (Theory)

● CNN architecture
● Convolution & pooling
● Transfer learning
● Image classification project idea

Class 21: Object Detection with YOLO and Faster R-CNN

● Object detection basics


● Bounding Boxes

Project: Real-Time Object Detection with YOLO

Assignment: Object Detection with Faster R-CNN

Class 22: Sequential Models (Theory)

● RNN
● LSTM
● GRU
● Sequence modeling
● Time-series DL use cases

Class 23: Sequential Models with Python

● Sequence modeling with Python

Project: End-to-End Sequence Predictor

Class 24: Transformer

● Transformer Architecture
● BERT Vs. DistilBERT

Project: Text Classification with BERT

[Link]
Assignment: Real Vs. AI-Generated Text Classifier

Class 25: Career Guidelines: What NEXT?

● Building a Professional Resume


● Job and Internship Guidelines
● Kaggle Competition
● Final Project Discussion

Contact Details:
Join Our Facebook Group: Join Now!
Call us: +8801704265972 (Direct Call / WhatsApp)
Talk with the Course Coordinator: Click Here!
Subscribe: Click Here!

[Link]

You might also like