Machine Learning + Image classification + TensorFlow 2.0

• An understanding of ___.
• Experience with ___.
• ___ programming experience.

Audience

• ___
• ___
• ___

1. Machine Learning introduction
   • Types of Machine learning – supervised vs unsupervised learning
   • From Statistical learning to Machine learning
   • The Data Mining workflow:
     • Business understanding
     • Data Understanding
     • Data preparation
     • Modelling
     • Evaluation
     • Deployment
   • Machine learning algorithms
   • Choosing appropriate algorithm to the problem
   • Overfitting and bias-variance tradeoff in ML
2. ML libraries and programming languages
   • Why use a programming language
   • Choosing between R and Python
   • Python crash course
   • Python resources
   • Python Libraries for Machine learning
   • Jupyter notebooks and interactive coding
3. Testing ML algorithms
   • Generalization and overfitting
   • Avoiding overfitting
     • Holdout method
     • Cross-Validation
     • Bootstrapping
   • Evaluating numerical predictions
     • Measures of accuracy: ME, MSE, RMSE, MAPE
     • Parameter and prediction stability
   • Evaluating classification algorithms
     • Accuracy and its problems
     • The confusion matrix
     • Unbalanced classes problem
   • Visualizing model performance
     • Profit curve
     • ROC curve
     • Lift curve
   • Model selection
   • Model tuning – grid search strategies
   • Examples in Python
4. Data preparation
   • Data import and storage
   • Understand the data – basic explorations
   • Data manipulations with pandas library
   • Data transformations – Data wrangling
   • Exploratory analysis
   • Missing observations – detection and solutions
   • Outliers – detection and strategies
   • Standarization, normalization, binarization
   • Qualitative data recoding
   • Examples in Python
5. Classification
   • Binary vs multiclass classification
   • Classification via mathematical functions
     • Linear discriminant functions
     • Quadratic discriminant functions
   • Logistic regression and probability approach
   • k-nearest neighbors
   • Naïve Bayes
   • Decision trees
     • CART
     • Bagging
     • Random Forests
     • Boosting
     • Xgboost
   • Support Vector Machines and kernels
     • Maximal Margin Classifier
     • Support Vector Machine
   • Ensemble learning
   • Examples in Python
6. Regression and numerical prediction
   • Least squares estimation
   • Variables selection techniques
   • Regularization and stability- L1, L2
   • Nonlinearities and generalized least squares
   • Polynomial regression
   • Regression splines
   • Regression trees
   • Examples in Python
7. Unsupervised learning
   • Clustering
     • Centroid-based clustering – k-means, k-medoids, PAM, CLARA
     • Hierarchical clustering – Diana, Agnes
     • Model-based clustering - EM
     • Self organising maps
     • Clusters evaluation and assessment
   • Dimensionality reduction
     • Principal component analysis and factor analysis
     • Singular value decomposition
   • Multidimensional Scaling
   • Examples in Python
8. Text mining
   • Preprocessing data
   • The bag-of-words model
   • Stemming and lemmization
   • Analyzing word frequencies
   • Sentiment analysis
   • Creating word clouds
   • Examples in Python
9. Recommendations engines and collaborative filtering
   • Recommendation data
   • User-based collaborative filtering
   • Item-based collaborative filtering
   • Examples in Python
10. Association pattern mining
    • Frequent itemsets algorithm
    • Market basket analysis
    • Examples in Python
11. Outlier Analysis
    • Extreme value analysis
    • Distance-based outlier detection
    • Density-based methods
    • High-dimensional outlier detection
    • Examples in Python
12. Machine Learning case study
    • Business problem understanding
    • Data preprocessing
    • Algorithm selection and tuning
    • Evaluation of findings
    • Deployment

Image classification + TensorFlow 2.0

13. Introduction to Deep Learning and TensorFlow
    • Creating, Initializing, Saving, and Restoring TensorFlow variables
    • Feeding, Reading and Preloading TensorFlow Data
    • Visualizing and Evaluating models with TensorBoard
14. TensorFlow Mechanics
    • Tutorial Files
    • Prepare the Data
      • Download
      • Inputs and Placeholders
    • Build the Graph
      • Inference
      • Loss
      • Training
    • Train the Model
      • The Graph
      • The Session
      • Train Loop
    • Evaluate the Model
      • Build the Eval Graph
      • Eval Output
15. TensorFlow Serving
16. Keras
17. Getting images from files and camera with OpenCV
18. Convolutional Neural Networks:
    • Overview
    • Building the digit classifier using MNIST dataset
19. Data augmentation
20. Pre-trained models (MobileNet) and transfer learning
21. Object detection
22. Image segmentation
23. Summary