Fundamentals of Artificial Intelligence and Machine Learning

Original price was: ₹10,000.00.Current price is: ₹5,000.00.

Course Includes:

  • Coach:Dr. Mahesh Patil
  • Date:Live
  • Lessons:12 Weeks
  • Students:250
  • Language:English
  • Certifications:Yes

Course Duration:

12 weeks (3 hours per week of lecture and 2 hours per week of lab work)

 

Course Description:

  • To understand the foundational concepts of Artificial Intelligence and Machine Learning.
  • To learn about essential ML algorithms and when to use them.
  • To develop practical skills in implementing ML models using Python and relevant libraries.
  • To gain insights into ethical considerations in AI.

Pre-requisites:

  • Basic programming knowledge (Python preferred).
  • Familiarity with basic mathematics, especially linear algebra and probability.

Course Outline:

Week 1-2: Introduction to Artificial Intelligence and Machine Learning

  • Lecture:
    • Overview of AI: Definitions, History, and Scope
    • Categories of AI: Narrow AI, General AI, and Superintelligent AI
    • AI Applications in real-world scenarios (e.g., Healthcare, Finance, Robotics)
    • Types of Machine Learning: Supervised, Unsupervised, Semi-Supervised, and Reinforcement Learning
  • Lab:
    • Python setup for ML: Anaconda, Jupyter Notebook, IDE setup
    • Introduction to Numpy, Pandas for data handling
  • Assignment:
    • Essay on current applications of AI in a chosen field

Week 3-4: Data Preprocessing and Exploration

  • Lecture:
    • Data Types and Sources in ML
    • Data Cleaning: Handling missing data, outliers, and encoding categorical data
    • Feature Scaling and Normalization
    • Introduction to Exploratory Data Analysis (EDA)
  • Lab:
    • Hands-on with Pandas for data cleaning and preprocessing
    • Using Matplotlib and Seaborn for data visualization
  • Assignment:
    • Exploratory analysis on a real-world dataset

Week 5-6: Supervised Learning – Regression and Classification

  • Lecture:
    • Overview of Supervised Learning
    • Linear Regression and Logistic Regression
    • Evaluation Metrics for Regression and Classification (e.g., MSE, RMSE, accuracy, F1 score)
  • Lab:
    • Implementing Linear and Logistic Regression models in Python (using Scikit-Learn)
    • Experiment with hyperparameter tuning
  • Assignment:
    • Predictive modeling project with a dataset (e.g., house price prediction)

Week 7-8: Advanced Supervised Learning – Decision Trees, SVMs, and Ensembles

  • Lecture:
    • Decision Trees and Random Forests
    • Support Vector Machines (SVM)
    • Ensemble Learning: Bagging, Boosting, and Stacking
  • Lab:
    • Hands-on with Decision Trees, Random Forest, and SVMs using Scikit-Learn
    • Implementing ensemble methods
  • Assignment:
    • Classification project on a dataset (e.g., customer segmentation)

Week 9: Unsupervised Learning – Clustering and Dimensionality Reduction

  • Lecture:
    • Clustering Algorithms: K-Means, Hierarchical Clustering
    • Dimensionality Reduction: PCA, t-SNE
  • Lab:
    • Applying K-Means and Hierarchical Clustering on datasets
    • Using PCA for dimensionality reduction and visualization
  • Assignment:
    • Clustering project on a dataset (e.g., text clustering)

Week 10: Neural Networks and Deep Learning Basics

  • Lecture:
    • Introduction to Neural Networks and the concept of Deep Learning
    • Activation Functions and Backpropagation
    • Basic architectures (feed-forward, CNN, RNN)
  • Lab:
    • Implementing a simple neural network using Keras
    • Using pre-trained models for image classification
  • Assignment:
    • Build a simple neural network model on a given dataset (e.g., MNIST digit classification)

Week 11: Ethics in AI and Bias in Machine Learning

  • Lecture:
    • Understanding biases in AI models
    • Ethical implications of AI in society (privacy, accountability, transparency)
    • Techniques to mitigate bias
  • Lab:
    • Analyzing a biased dataset and using mitigation techniques
  • Assignment:
    • Write a report on ethical considerations for a selected AI application

Week 12: Model Deployment and Course Project

  • Lecture:
    • Overview of Model Deployment: On-premises, Cloud, Edge Deployment
    • Deployment options and considerations
    • Course recap and Q&A
  • Lab:
    • Deploying a trained ML model with Flask or Streamlit
  • Final Project:
    • End-to-end project: Data preprocessing, model selection, training, evaluation, and deployment.

Course Materials:

  • Textbook: “Machine Learning” by Tom M. Mitchell
  • Supplementary Resources:
    • Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow by Aurélien Géron
    • Python Data Science Handbook by Jake VanderPlas

Evaluation Criteria:

  • Assignments and Labs: 40%
  • Mid-term Exam: 20%
  • Final Project: 30%
  • Participation and Quizzes: 10%

This course provides a strong foundation in AI and ML, with an emphasis on understanding key algorithms and the ability to implement them practically. It also ensures students gain a holistic view of the field, including ethical implications.