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

Introduction to Applied Machine Learning

• Distinctions between statistical learning and Machine Learning
• Iteration and evaluation processes
• The Bias-Variance trade-off
• Comparing Supervised and Unsupervised Learning
• Challenges addressed by Machine Learning
• Train, Validation, and Test splits – ML workflows to prevent overfitting
• General Machine Learning workflow
• Overview of Machine learning algorithms
• Selecting the appropriate algorithm for specific problems

Algorithm Evaluation

• Assessment of numerical predictions
  • Accuracy metrics: ME, MSE, RMSE, MAPE
  • Stability of parameters and predictions
• Evaluation of classification algorithms
  • Accuracy and its inherent limitations
  • Utilizing the confusion matrix
  • Addressing the class imbalance problem
• Visualization of model performance
  • Profit curves
  • ROC curves
  • Lift curves
• Model selection strategies
• Model tuning – grid search methodologies

Data Preparation for Modelling

• Data importation and storage protocols
• Data comprehension – basic explorations
• Data manipulation using the pandas library
• Data transformations – Data wrangling techniques
• Exploratory data analysis
• Handling missing observations – detection and remediation
• Outliers – identification and handling strategies
• Standardization, normalization, and binarization
• Recoding 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
• Differentiating Machine Learning from Deep Learning
• Survey of Deep Learning Applications

Overview of Neural Networks

• Definition of Neural Networks
• Neural Networks versus Regression Models
• Mathematical Foundations and Learning Mechanisms
• Constructing Artificial Neural Networks
• Neural Nodes and Connection Structures
• Working with Neurons, Layers, and Input/Output Data
• Single Layer Perceptrons explained
• Contrasts between Supervised and Unsupervised Learning
• Feedforward and Feedback Neural Networks
• Forward Propagation and Back Propagation mechanisms

Building Basic Deep Learning Models with Keras

• Initiating a Keras Model
• Data Interpretation and Understanding
• Defining the Deep Learning Model structure
• Model Compilation process
• Fitting the Model to data
• Handling Classification Data
• Developing Classification Models
• Deploying and Using Models

Utilizing TensorFlow for Deep Learning

• Data Preparation Phase
  • Data Acquisition
  • Preparation of Training Datasets
  • Preparation of Test Datasets
  • Input Scaling techniques
  • Utilization of Placeholders and Variables
• Network Architecture Definition
• Application of Cost Functions
• Optimizer Configuration
• Setting Initializers
• Neural Network Fitting
• Graph Construction
  • Inference steps
  • Loss calculation
  • Training logic
• Model Training Execution
  • The Graph component
  • The Session component
  • Train Loop implementation
• Model Evaluation
  • Constructing the Eval Graph
  • Evaluation via Eval Output
• Training Models at Scale
• Model Visualization and Evaluation using TensorBoard

Deep Learning Applications in Anomaly Detection

• Autoencoder
  • Encoder - Decoder Architectures
  • Reconstruction Loss metrics
• Variational Autoencoder
  • Variational inference techniques
• Generative Adversarial Networks
  • Generator – Discriminator Architectures
  • Anomaly Detection approaches using GANs

Ensemble Frameworks

• Aggregating results from diverse methods
• Bootstrap Aggregating (Bagging)
• Averaging of outlier scores