Course curriculum

  • 1

    Introduction to the Course

    • Introduction to the Deep Neural Networks
    • Why Deep learning Networks (DNN)
  • 2

    Introduction to Machine Learning

    • Introduction to Machine Learning, Learning Process and Supervised Learning
    • UnSupervised Learning and Reinforcement Learning
    • History and Future of Machine Learning
    • Dataset, Label and Features
    • Training Data,Testing Data and Outliers
    • Machine Learning Model
    • Difference between Classification and Regression
    • Function, Parameters and Hyperparameters
    • Model Training, Cost, Error, Loss, Risk and Accuracy
    • Optimization
    • Overfitting, Underfitting and Just Right Optimum (Part 1)
    • Overfitting, Underfitting and Just Right Optimum (Part 2)
    • Validation and Cross Validation,Generalization,Data Snooping,Validation Set
    • Probability Distributions and Curse of Dimensionlity
    • Small Sample Size problems,One Shot Learning
    • Importance of Data in Machine Learning,Data Encoding and Preprocessing
    • General Flow of a typical Machine Learning Project
  • 3

    Introduction to Python

    • Introduction to Python
    • Introduction to IDE,Hello World
    • Introduction to Data Type, Numbers
    • Variable and Operators (Numbers)
    • Variables and Operators (Rational Operators and Functions)
    • Variables and Operators (String)
    • Variables and Operators (String and print Statement)
    • Lists(Indexing,Slicing-Built in Lists Functions)
    • Lists(Copying a List)
    • Tuples(Indexing,Slicing,Built in Tuple Functions)
    • Set(initialize,Built in Set Functions)
    • Dictionary
    • Logical Operator,Decision Making,For Loops,While Loops,Functions
    • Logical Operator,Decision Making,For Loops,While Loops,List Comprehension
    • Functions
    • Calculator Project
  • 4

    Deep Neural Networks and Deep Learning Basics

    • Introduction to Artificial Neural Networks
    • Neuron and Perceptron
    • Deep Neural Network Architecture
    • FeedForward fully Connected MLP
    • Calculating Number of weights of DNN
    • Number Of Neurons Vs Number Of Layers
    • Discriminative Vs Generative Learning
    • Universal Approximation Theorem
    • Why Depth
    • Decision Boundary in DNN
    • Bias Term
    • The Activation Function
    • DNN Training Parameters
    • Gradient Descent
    • Backpropagation
    • Training DNN Animantion
    • Weigth Initialization
    • Batch MiniBatch Stocastic
    • Batch Normalization
    • Rprop Momentum
    • convergence Animation
    • Drop Out Early Stopping Hyperparameters
  • 5

    Python for Data Science

    • Python Packages for Data Science
    • NumPy Pandas and Matplotlib (Part 1)
    • NumPy Pandas and Matplotlib (Part 2)
    • NumPy Pandas and Matplotlib (Part 3)
    • NumPy Pandas and Matplotlib (Part 4)
    • NumPy Pandas and Matplotlib (Part 5)
    • NumPy Pandas and Matplotlib (Part 6)
    • DataSet Preprocessing
    • TensorFlow for classification
  • 6

    Implementation of DNN for COVID 19 Analysis

    • COVID19 Data Analysis
    • COVID19 Regression with TensorFlow
  • 7

    Optional Course for Maths behind DNN

    • Understanding Gradient Decsent
    • Understanding Gradient Decsent