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

Introduction to Applied Machine Learning

• Comparing statistical learning with machine learning
• The process of iteration and evaluation
• The Bias-Variance trade-off
• Supervised versus Unsupervised Learning
• Problems addressed by Machine Learning
• Train, Validation, Test – The ML workflow to prevent overfitting
• The Machine Learning workflow
• Overview of machine learning algorithms
• Selecting the appropriate algorithm for specific problems

Evaluating Algorithms

• Assessing numerical predictions
  • Accuracy metrics: ME, MSE, RMSE, MAPE
  • Stability of parameters and predictions
• Assessing classification algorithms
  • Accuracy and its limitations
  • The confusion matrix
  • The issue of unbalanced classes
• Visualizing model performance
  • Profit curve
  • ROC curve
  • Lift curve
• Selecting the best model
• Model tuning – grid search strategies

Data Preparation for Modelling

• Importing and storing data
• Gaining data insights through basic exploration
• Manipulating data using the pandas library
• Data transformations – Data wrangling
• Conducting exploratory analysis
• Handling missing observations – detection and remedies
• Managing outliers – detection and 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

Comprehending Deep Learning

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

Neural Networks Overview

• 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 Feedforward and Feedback Neural Networks
• Understanding Forward Propagation and Back Propagation

Creating Basic Deep Learning Models with Keras

• Building a Keras Model
• Understanding the dataset
• Defining the Deep Learning model structure
• Compiling the model
• Fitting the model
• Handling classification data
• Working with classification models
• Deploying your models

Utilizing TensorFlow for Deep Learning

• Preparing the Data
  • Downloading the dataset
  • Preparing training data
  • Preparing test data
  • Scaling inputs
  • Using Placeholders and Variables
• Defining the Network Architecture
• Utilizing the Cost Function
• Using the Optimizer
• Using Initializers
• Fitting the Neural Network
• Constructing the Graph
  • Inference
  • Loss
  • Training
• Training the Model
  • The Graph
  • The Session
  • The Training Loop
• Assessing the Model
  • Building the Evaluation Graph
  • Evaluating with Output
• Training Models at Scale
• Visualizing and Assessing Models with TensorBoard

Deep Learning Applications in Anomaly Detection

• Autoencoders
  • Encoder-Decoder Architecture
  • Reconstruction loss
• Variational Autoencoders
  • Variational inference
• Generative Adversarial Networks (GANs)
  • Generator-Discriminator architecture
  • Approaches to Anomaly Detection using GANs

Ensemble Frameworks

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