Curriculum

Machine Learning & Deep Learning with Python

Module-1: Introduction to Artificial Intelligence & Machine Learning
  • What is Artificial Intelligence
  • History of Artificial Intelligence
  • Use Cases of Artificial Intelligence
  • What is data science
  • Why is it important
  • Use Cases of Data Science
  • The Various Data Science Disciplines
  • Data Science and Business Buzzwords
  • What is the difference between Analysis and Analytics
  • ML In Data Science
  • Machine Learning Tools & Packages
  • Data Science Methodology

Module-2: Python for Data Science
  • Python Basics
  • Python Packages
  • Working with NUMPY
  • Working with Pandas 
  • Introduction to Data Visualization
  • Exploratory Data Analysis with Matplotlib and Seaborn
  • Basic Plotting with Matplotlib and Seaborn

Module-3: Mathematics for Data Science
Descriptive Statistics:
    1. Introduction to descriptive Statistics
    2. Mean, Median, Mode
    3. Skewness
    4. Range & IQR
    5. Sample vs. Population
    6. Variance & Standard deviation
    7. Impact of Scaling & Shifting
Distributions:
  • What is a distribution?
  • Normal distribution
    1. Z-Scores
    2. Central Limit Theorem
    3. Hypothesis Testing
    4. Correlation, And Regression
    5. Linear Algebra
    6. Calculus

Module-4: Data Wrangling Techniques
  • Introduction to Data preprocessing
  • Importing the Dataset
  • Handling Missing data
  • Working with categorical Data
  • Splitting the data into Train and Test set
  • Outlier Analysis
  • Feature Scaling

Module-5: Supervised Learning - Regression
  • Introduction to Regression
  • Linear Regression
  • Multi Linear Regression
  • Polynomial Regression
  • Ridge Regression
  • Lasso Regression

Module-6: Supervised Learning - Classification
  • Introduction to Classification
  • Logistic Regression
  • Decision Tree Classification
  • Random Forest Classification
  • K-nearest Neighbors
  • Naïve-Bayes
  • Support Vector Machine
  • Ensembling Techniques

Module-7: Model Evaluation Metrics
Regression Evaluation Metrics
  1. MAE
  2. MSE
  3. R Squared
  4. RMSE
Classification metrics
  1. Confusion Metrics
  2. Accuracy
  3. Precision
  4. Recall F1 Score
  5. AUC ROC Curves

Module-8: Model Hyper-parameter Optimization
Handling Imbalanced Data
  1. Oversampling
  2. Undersampling
  3. Ensembling Techniques
  4. SMOTE 
Hyper-parameter tuning
  1. Grid Search
  2. Randomize Search

Module-9: Unsupervised Learning
Introduction to Clustering
  1. K-Means Clustering
  2. Hierarchical Clustering
  3. Clustering use cases

Module-10: Introduction to Neural Networks
  • The Neuron 
  • The Activation Function 
  • How do Neural Networks work? 
  • How do Neural Networks learn? 
  • Gradient Descent 
  • Stochastic Gradient Descent 
  • Backpropagation

Module-11: Tensorflow & Keras
  • Introduction to Tensorflow & Keras Framework 
  • Introduction to the Sequential Mode
  • Activation functions 
  • Layers 
  • Training 
  • Loss function 
  • Building ANN Using Tensor flow
  • Evaluating Improving and Tuning ANN

Module-12: Convolutional Neural Networks
  • Introduction to Convolutional Neural Networks 
  • What are convolutional neural networks? 
    • Step 1 - Convolution Operation  
    • Step 2 - Pooling 
    • Step 3 - Flattening 
    • Step 4 - Full Connection Classification of images using CNN 
  • Evaluating, Improving, and Tuning the CNN 
  • Video Analysis using OpenCV
  • Object detection using YOLO

Module-13: Transfer Learning
  • Introduction to Transfer Learning Models
  • How does Transfer Learning work
  • When should we use Transfer Learning
  • Approaches to transfer Learning
  1. Inception V3
  2. Xception
  3. Resnet-50
  4. VGG-19

Module-14: Recurrent Neural Networks
  • Introduction to Recurrent Neural Networks 
  • The idea behind Recurrent Neural Networks 
  • The Vanishing Gradient Problem 
  • LSTMs 
  • LSTM Variations Predicting Google stock prices using RNN 
  • Evaluating, Improving, and Tuning the RNN

Module-15: Natural Language Processing
  • Introduction to Natural Language Processing 
  • Introduction to NLTK 
  • Bag of Words model 
  • Natural Language Processing in Python 
  • Sentiment analysis using Natural Language Processing

Module-16: Build and Deploy an AI Application
  • Introduction to different modes of Deployments
  • Working with Flask framework 
  • Building an application with Flask Framework 
  • Integrating Deep learning model with Web Application
SmartInternz