Artifical Intelligence

Course Description

Artifical Intelligence

This AI, Machine Learning (ML), and Deep Learning (DL) course is designed to introduce students to the fascinating world of artificial intelligence, providing them with essential knowledge and skills that will be valuable across multiple industries. The course begins by exploring the fundamentals of AI, guiding students through its history, core goals, and the different types of AI, including Narrow AI, General AI, and Superintelligent AI. By understanding these distinctions, students will grasp how AI operates and its growing influence in modern society.

As the course progresses, learners will delve into the critical concepts of machine learning, focusing on both supervised and unsupervised learning. They will discover how ML models are built, trained, and evaluated, gaining hands-on experience with algorithms that power many AI applications today. Through practical examples and exercises, students will see how these models can be applied to various tasks such as classification, regression, and clustering, providing a strong foundation in data-driven decision-making.

The course also introduces students to the exciting realm of deep learning, explaining how neural networks function and why they are instrumental in advancing AI technologies. From image recognition to speech processing, deep learning is at the core of many cutting-edge innovations, and students will learn how these models are developed to solve complex problems that require high-level cognitive functions. By the end of the course, students will have a clear understanding of how AI, ML, and DL are shaping industries like healthcare, finance, and robotics, equipping them with the tools needed to pursue further studies or a career in artificial intelligence.

 

    • Introduction to AI

      • History of AI
      • Core Concepts
      • Types of AI
      • Ethics in AI

      Comparison of AI - ML - DL

      • Relation of AI - ML - DL
      • Machine Learning
      • Deep Learning

      Machine Learning

      • Working of ML
      • Types of ML
      • Implementation and working of Classification
      • Implementation and working of Regression

      Working of a Model

      • Introduction to Decision Tree
      • Model Creation
      • Model Validation
      • Underfitting and Overfitting
      • Random Forests

      Unsupervised Learning

      • Introduction to Unsupervised Learning
      • Clustering
      • K-means clustering

      Data Visualization

      • Line charts
      • Bar charts
      • Heat maps

      Data Preparation

      • Importance of Data Preparation
      • Misconceptions about Data Preparation
      • Steps of Data Preparation

      Deep Learning

      • Linear Unit
      • Deep neural networks
      • Layers
      • Activation Functions
      • Training the models
      • Loss functions
      • Optimizers
      • Learning rate and batch size
      • Interpreting Line curves
      • Early stopping
      • Dropout
      • Batch normalisation

      Binary Classification

      • Introduction
      • Accuracy and Cross-entropy
      • Sigmoid Activation

      CNN

      • Introduction to CNN
      • How does it recogonize images
      • Layers in CNN
      • Training CNN
      • Evaluation of CNN
      • Types of CNN
      • Applications of CNN
      • Advantages of CNN
      • Implementation of a Digit Classifier

       

Reviews

Average Rating

0
(0 ratings)

Detailed Rating

0%
0%
0%
0%
0%