Scribd
Upload
38 views5 pages

AIML 2nd Year

The document outlines a comprehensive Machine Learning curriculum for 2nd-year students, covering Python programming, data analysis, statistics, data visualization, machine learning, and deep learning. It includes detailed units on various topics such as supervised and unsupervised learning, neural networks, and practical projects like predicting employee attrition and developing recommendation systems. The curriculum emphasizes hands-on projects to apply theoretical knowledge in real-world scenarios.

Uploaded by

ar9029
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
38 views5 pages

AIML 2nd Year

The document outlines a comprehensive Machine Learning curriculum for 2nd-year students, covering Python programming, data analysis, statistics, data visualization, machine learning, and deep learning. It includes detailed units on various topics such as supervised and unsupervised learning, neural networks, and practical projects like predicting employee attrition and developing recommendation systems. The curriculum emphasizes hands-on projects to apply theoretical knowledge in real-world scenarios.

Uploaded by

ar9029
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

MACHINE LEARNING

2ND YEAR
Unit I: Python Programming and Data Analysis Fundamentals (10 Hours)

 Essentials of Python Programming


• Introduction to Python
• Python Data Types and Operators
• Control Flow: Loops and Conditional Statements
• Functions and Modules
• Object-Oriented Programming in Python
 Fundamentals of NumPy
• NumPy Arrays and Operations
• Mathematical Operations on NumPy Arrays
• Array Broadcasting
• Random Sampling with NumPy
 Linear Algebra
• Vectors and Matrices
• Matrix Multiplication
• Eigenvalues and Eigenvectors

Unit II: Statistics, Probability, and Data Wrangling (10 Hours)

 Statistics Fundamentals
• Descriptive Statistics (Mean, Median, Mode, Variance, Standard Deviation)
• Data Distribution and Skewness
• Sampling and Sampling Distributions
 Probability Distributions
• Normal Distribution
• Binomial Distribution
• Poisson Distribution
• Central Limit Theorem
 Advanced Statistics
• Hypothesis Testing (t-tests, Chi-Square)
• Confidence Intervals
• Statistical Power and Effect Size
 Working with Pandas
• DataFrames and Series
• Data Cleaning and Manipulation
• Merging, Joining, and Grouping Data
• Handling Missing Data
 Data Wrangling
• Data Transformation Techniques
• Data Aggregation and Grouping
• Time Series Data Handling
Unit III: Data Visualization and Analysis in Python (10 Hours)

 Data Visualization
• Introduction to Data Visualization Tools
• Matplotlib Basics
• Seaborn for Statistical Plots
• Plotly for Interactive Plots
• Customizing Plots and Charts
 End-to-End Statistics Application in Python
• Data Collection and Cleaning
• Applying Statistical Models in Python
• Visualizing the Results of Statistical Models
• Drawing Insights from Data and Statistics

Unit IV: Machine Learning (10 Hours)

 Supervised Learning
• Introduction to Supervised Learning
• Model Training and Validation
• Overfitting and Underfitting
 Regression Models and Applications
• Linear Regression
• Logistic Regression
• Regularization (Lasso, Ridge)
• Evaluation Metrics (MSE, RMSE, MAE)
 Classification Models and Applications
• K-Nearest Neighbors (KNN)
• Decision Trees and Random Forests
• Support Vector Machines (SVM)
• Model Evaluation (Accuracy, Precision, Recall, F1-Score)
 Unsupervised Learning
• Clustering (K-Means, DBSCAN)
• Dimensionality Reduction (PCA, t-SNE)
 Ensemble Learning
• Bagging and Boosting
• Random Forests
• Gradient Boosting Machines (GBM)
• XGBoost and LightGBM
 Recommendation Systems
• Collaborative Filtering
• Content-Based Filtering
• Hybrid Models
Unit V: Deep Learning Specialization (10 Hours)

 Introduction to Deep Learning


• Basics of Deep Learning
• Neural Networks Architecture
• Activation Functions (ReLU, Sigmoid, Tanh)
 Artificial Neural Networks
• Perceptrons and Feedforward Networks
• Backpropagation and Gradient Descent
 Deep Neural Networks (DNNs)
• Multi-Layer Neural Networks
• Training Deep Networks
• Overcoming Overfitting in DNNs
 TensorFlow
• Introduction to TensorFlow
• TensorFlow Basics (Tensors, Operations)
• Building Neural Networks in TensorFlow
 Convolutional Neural Networks (CNNs)
• Understanding CNNs
• CNN Architecture and Layers
• Applications in Image Classification
 Model Optimization and Performance Improvement
• Hyperparameter Tuning
• Regularization Techniques
• Batch Normalization
• Early Stopping
 Transfer Learning
• Using Pretrained Models
• Fine-tuning Pretrained Networks
 Object Detection
• Overview of Object Detection Techniques
• YOLO (You Only Look Once)
 PyTorch
• Introduction to PyTorch
• Building and Training Models with PyTorch
 Recurrent Neural Networks (RNNs)
• RNN Architecture
• Applications in Time Series and Sequential Data
 Getting Started with Autoencoders
• Autoencoders for Dimensionality Reduction
• Anomaly Detection Using Autoencoders
 Transformer Models for NLP
• Introduction to Transformers
• Attention Mechanism
• Applications in Natural Language Processing (NLP)
PROJECTS
MLB Digital Platform Enhancement
Develop a backend for MLB's digital platform to manage player statistics, match schedules, and ticket
bookings, and implement a report generation system to enhance performance.
EdTech Backend System
Create backend modules for SL Tech's edtech platform to manage learner credentials, courses, and
improve the overall learning experience.
Sales Strategy Analysis
Analyze AAL's sales data across different Australian states to identify high-revenue states and
develop sales programs for underperforming states.

Marketing Strategies with Exploratory Data Analysis


Conduct exploratory data analysis and hypothesis testing to understand factors contributing to
customer acquisition and enhance marketing strategies.

Predicting Employee Attrition with Machine


Build a machine learning model to predict employee attrition by analyzing work habits and factors
influencing their desire to stay with the company.

Song Classification with Cluster Analysis


Perform cluster analysis to create personalized song playlists for users based on their listening
behavior.

Home Loan Data Analysis


Develop a deep learning model to predict the likelihood of loan defaults using historical data,
ensuring a secure lending process.

Lending Club Loan Data Analysis


Create a deep learning model to predict loan defaults using historical data, addressing an imbalanced
dataset with numerous features.

ChatGPT Based Storytelling


Design an interactive storytelling adventure using ChatGPT to create unique and engaging narratives
without coding collaboratively.

Virtual Project Management Consultant


Develop prompts for ChatGPT to function as a virtual project management consultant, providing
advice on project planning, risk management, team collaboration, and performance.

AI-Powered HR Assistant with GPT and Gradio


Develop an AI-driven HR assistant that extracts answers from Nestle’s HR policy documents using
OpenAI's GPT model and Gradio UI.

Text-to-Design Platform with DALL-E and Gradio


Create a platform that transforms text prompts into striking designs using OpenAI’s DALL-E and
Gradio UI. Explore AI’s impact on digital content creation for marketing.

Road Safety Analysis of Autopilot Feature


Analyze accident data involving Tesla’s autopilot feature to assess the impact of autopilot technology
on road safety.

AI Recommendation Engine for Marketing


Use AI to understand the state of historical structures and recommend the best places to visit to
tourists.

Predict the Demand and Sales of a Restaurant


Predict demand for various items across restaurants using machine learning and deep learning
algorithms to forecast sales over time.

Diabetic Retinopathy Detection with CNN and TensorFlow


Use distributed training and TensorFlow serving to build and deploy a CNN model for automated
diabetic retinopathy detection.

Build Facial Recognition System with Deep Learning


Leverage deep learning algorithms to develop a facial recognition model that assists in diagnosing
genetic disorders and their variations in patients.

You might also like