Fundamentals of Artificial Intelligence (AI) and Machine Learning Training Course

Introduction to Applied Machine Learning

• Statistical learning versus Machine Learning
• Iteration and evaluation
• Bias-Variance trade-off
• Supervised versus Unsupervised Learning
• Problems solved by Machine Learning
• Train, Validation, Test – ML workflow to prevent overfitting
• Machine Learning workflow
• Machine learning algorithms
• Selecting the appropriate algorithm for the problem

Algorithm Evaluation

• Evaluating numerical predictions
  • Measures of accuracy: ME, MSE, RMSE, MAPE
  • Parameter and prediction stability
• Evaluating classification algorithms
  • Accuracy and its limitations
  • The confusion matrix
  • The issue of unbalanced classes
• Visualising model performance
  • Profit curve
  • ROC curve
  • Lift curve
• Model selection
• Model tuning – grid search strategies

Data Preparation for Modelling

• Data import and storage
• Understanding the data – basic explorations
• Data manipulation using the pandas library
• Data transformations – Data wrangling
• Exploratory analysis
• Missing observations – detection and solutions
• Outliers – detection and strategies
• Standardisation, normalisation, binarisation
• Recoding qualitative data

Machine Learning Algorithms for Outlier Detection

• Supervised algorithms
  • KNN
  • Ensemble Gradient Boosting
  • SVM
• Unsupervised algorithms
  • Distance-based
  • Density-based methods
  • Probabilistic methods
  • Model-based methods

Understanding Deep Learning

• Overview of fundamental Deep Learning concepts
• Differentiating between Machine Learning and Deep Learning
• Overview of Deep Learning applications

Overview of Neural Networks

• What are Neural Networks
• Neural Networks versus Regression Models
• Understanding Mathematical Foundations and Learning Mechanisms
• Constructing an Artificial Neural Network
• Understanding Neural Nodes and Connections
• Working with Neurons, Layers, and Input/Output Data
• Understanding Single Layer Perceptrons
• Differences between Supervised and Unsupervised Learning
• Learning Feedforward and Feedback Neural Networks
• Understanding Forward Propagation and Back Propagation

Building Simple Deep Learning Models with Keras

• Creating a Keras Model
• Understanding Your Data
• Specifying Your Deep Learning Model
• Compiling Your Model
• Fitting Your Model
• Working with Your Classification Data
• Working with Classification Models
• Utilising Your Models

Working with TensorFlow for Deep Learning

• Preparing the Data
  • Downloading the Data
  • Preparing Training Data
  • Preparing Test Data
  • Scaling Inputs
  • Using Placeholders and Variables
• Specifying the Network Architecture
• Using the Cost Function
• Using the Optimizer
• Using Initializers
• Fitting the Neural Network
• Building the Graph
  • Inference
  • Loss
  • Training
• Training the Model
  • The Graph
  • The Session
  • Training Loop
• Evaluating the Model
  • Building the Evaluation Graph
  • Evaluating with Evaluation Output
• Training Models at Scale
• Visualising and Evaluating Models with TensorBoard

Application of Deep Learning in Anomaly Detection

• Autoencoder
  • Encoder - Decoder Architecture
  • Reconstruction loss
• Variational Autoencoder
  • Variational inference
• Generative Adversarial Network
  • Generator – Discriminator architecture
  • Approaches to AN using GAN

Ensemble Frameworks

• Combining results from different methods
• Bootstrap Aggregating
• Averaging outlier scores