Machine learning

Machine learning Diploma



Module one: Python (24h)

o Why python?
o python with AI and ML
o Input & Output
o Variables
o Data types
o Boolean & Comparison and Logic
o If Conditions
o For Loops
o Built-in functions & Operators
o Numbers & Math
o Functions
o Variables Scope
o Modules
o Command Lines
o File Handling
Object-Oriented Programming (OOP)
o Strings
o Special Functions
o Classes
o Inheritance
o Regular expressions
o Working with files
o Python generators

Module Two: Data Preprocessing & OpenCv (24h)

o Create Numpy Array
o Indexing
o Arithmetic and Logic
o Universal Array Functions

  • Pandas
    o Series
    o Data Frames
    o Data Input & Output
    o Useful Methods
    o Apply function
    o Grouping data and aggregate functions
    o Merging, Joining and Concatenating
    o Pivoting
  • OpenCV
    o Read images
    o Color spaces
    o Operations on images
    o Draw shapes
    o Edge detection
    o Cascade classifier
    o Video stream
    o Real time detection

Module Three: Machine Learning (20h)

Introduction to ML
o The difference between ML, Big data, Data analysis and Deep Learning
o Linear Algebra and Statistics for ML
o Data preprocessing

Regression problem
o Linear Regression
o Multi-linear regression
o Polynomial regression
o K-nearest neighbor regression
o Decision tree regression
o Regression Evaluation Metrics

Classification problem
o Logistic Regression
o Naive Bayes
o K-nearest neighbor classifier
o Support vector machine (SVM)
o Decision tree classifier
o Ensemble learning
o Classification Evaluation Metrics
o Random Forests
o XGBoost

Clustering Problems
o Dimensionality reduction
o K-means
o hierarchical clustering
o Association Rules

Model Selection and evaluation
o Loss functions
o Gradient descent
o Bias-variance tradeoff
o Cross-validation
o Hyper parameter tuning

Module Four: Artificial Neural Networks (20h)

Difference between AI, DL, ML and ANN
Introduction to Neural Networks
Deep Learning with Pytorch
Linear Regression
Binary Classification
Logistic Regression
Gradient Descent
Deep layer neural network
Forward and Backward Propagation
Regularization and Dropout
Adam optimization algorithm
Tuning process
Multi Classification with Deep Learning
Transfer learning


Module Five: Computer vision (24h)

Introduction to Computer Vision
CNN Architecture
Padding & Stride Convolutions
Pooling Layers
Convolutional Neural Networks & Datasets
Multiclass classification
Object Detection
Non-max Suppression
YOLO Algorithm
Face Verification and Binary Classification

Module Six: Natural Language processing (36h)

  • String preprocessing (re)
    • Embedding & Word2Vec
    • RNN
    • LSTM & GRU
    • Text classification
    • LDA
    • Glove
    • Language Modeling
    • Text Generation
    • Auto correct
    • Text classification
    • LDA
    • ChatGPT