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

Introduction to Applied Machine Learning

• Statistical learning compared with Machine learning
• Iterative processes and model evaluation
• The Bias-Variance trade-off
• Distinction between Supervised and Unsupervised Learning
• Challenges addressed by Machine Learning
• Train, Validation, and Test sets – ML workflow strategies to prevent overfitting
• The end-to-end Machine Learning workflow
• Core Machine learning algorithms
• Selecting the optimal 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 inherent limitations
  • Utilizing the confusion matrix
  • Addressing class imbalance issues
• Visualizing model performance
  • Profit curves
  • ROC curves
  • Lift curves
• Model selection strategies
• Model tuning via grid search techniques

Data Preparation for Modelling

• Importing and storing data
• Initial data exploration and understanding
• Manipulating data using the pandas library
• Data transformation and wrangling
• Conducting exploratory data analysis
• Detecting and handling missing observations
• Identifying outliers and applying mitigation strategies
• Standardization, normalization, and binarization
• Recoding qualitative data

Machine learning algorithms for Outlier detection

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

Understanding Deep Learning

• Fundamental concepts of Deep Learning
• Distinguishing Machine Learning from Deep Learning
• Overview of Deep Learning applications

Overview of Neural Networks

• Definition and nature of Neural Networks
• Neural Networks versus Regression Models
• Mathematical foundations and learning mechanisms
• Constructing Artificial Neural Networks
• Structure of Neural Nodes and Connections
• Managing Neurons, Layers, and Input/Output Data
• Single Layer Perceptrons explained
• Variations between Supervised and Unsupervised Learning
• Feedforward and Feedback Neural Networks
• Forward Propagation and Back Propagation processes

Building Simple Deep Learning Models with Keras

• Initializing a Keras Model
• Interpreting and understanding the dataset
• Defining the Deep Learning model structure
• Compiling the model configuration
• Fitting the model to data
• Processing classification data
• Developing classification models
• Deploying and using trained models

Working with TensorFlow for Deep Learning

• Data Preparation
  • Acquiring datasets
  • Preparing training data
  • Preparing test data
  • Scaling input features
  • Utilizing Placeholders and Variables
• Defining the Network Architecture
• Implementing Cost Functions
• Selecting and applying Optimizers
• Utilizing Initializers
• Training the Neural Network
• Constructing the Computational Graph
  • Inference operations
  • Loss calculation
  • Training operations
• Executing Model Training
  • Graph structure
  • Session management
  • Implementing the training loop
• Model Evaluation
  • Building the evaluation graph
  • Analyzing evaluation outputs
• Scaling Model Training
• Visualizing and evaluating models using TensorBoard

Application of Deep Learning in Anomaly Detection

• Autoencoders
  • Encoder-Decoder structure
  • Reconstruction loss metrics
• Variational Autoencoders
  • Variational inference techniques
• Generative Adversarial Networks (GANs)
  • Generator-Discriminator architecture
  • Anomaly detection approaches using GANs

Ensemble Frameworks

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