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

Introduction to Applied Machine Learning

• Statistical learning compared to machine learning
• Iteration and evaluation processes
• Bias-Variance trade-off
• Supervised versus Unsupervised Learning
• Challenges addressed by Machine Learning
• Train, Validation, Test – ML workflow to prevent overfitting
• Machine Learning workflow
• Machine learning algorithms
• Selecting the appropriate algorithm for specific problems

Algorithm Evaluation

• Assessing numerical predictions
  • Accuracy metrics: ME, MSE, RMSE, MAPE
  • Stability of parameters and predictions
• Assessing classification algorithms
  • Accuracy and its associated limitations
  • The confusion matrix
  • Handling unbalanced class problems
• Visualizing 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 data analysis
• Missing observations – identification and resolution
• Outliers – identification and management strategies
• Standardization, normalization, and binarization
• Recoding of qualitative data

Machine Learning Algorithms for Outlier Detection

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

Understanding Deep Learning

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

Overview of Neural Networks

• Definition of Neural Networks
• Neural Networks compared to 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 about Feedforward and Feedback Neural Networks
• Understanding Forward Propagation and Back Propagation

Building Simple Deep Learning Models with Keras

• Creating a Keras Model
• Understanding your dataset
• Defining your Deep Learning model structure
• Compiling the model
• Fitting the model to data
• Working with classification data
• Implementing classification models
• Utilizing trained models

Working with TensorFlow for Deep Learning

• Data Preparation
  • Downloading datasets
  • Preparing training data
  • Preparing test data
  • Scaling inputs
  • Using placeholders and variables
• Defining the network architecture
• Applying the cost function
• Selecting the optimizer
• Using initializers
• Fitting the Neural Network
• Constructing the Graph
  • Inference
  • Loss calculation
  • Training process
• Model Training
  • The Graph structure
  • The Session management
  • Train Loop implementation
• Model Evaluation
  • Constructing the Eval Graph
  • Evaluating based on Eval Output
• Training Models at Scale
• Visualizing and evaluating models using 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 anomaly detection using GAN

Ensemble Frameworks

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