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

Introduction to Applied Machine Learning

• Statistical learning versus machine learning
• Iterative processes and evaluation techniques
• The Bias-Variance trade-off
• Supervised versus Unsupervised Learning
• Challenges addressable through Machine Learning
• Train, Validation, and Test splits – ML workflows to prevent overfitting
• The Machine Learning workflow
• Overview of 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
• Evaluating classification algorithms
  • Accuracy and its associated limitations
  • Interpretation of the confusion matrix
  • Handling the problem of unbalanced classes
• Visualizing model effectiveness
  • Profit curve
  • ROC curve
  • Lift curve
• Model selection strategies
• Model tuning – grid search approaches

Data Preparation for Modeling

• Importing and storing data
• Understanding the data – fundamental explorations
• Manipulating data with the pandas library
• Data transformations – Data wrangling
• Exploratory data analysis
• Handling missing observations – detection and resolution
• 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
• Distinguishing between Machine Learning and Deep Learning
• Surveying applications for Deep Learning

Overview of Neural Networks

• Definition and nature of Neural Networks
• Neural Networks compared to Regression Models
• Exploring Mathematical Foundations and Learning Mechanisms
• Constructing an Artificial Neural Network
• Comprehending 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 the underlying data
• Defining the Deep Learning model architecture
• Compiling the model
• Fitting the model to data
• Processing classification data
• Utilizing classification models
• Deploying and using trained models

Working with TensorFlow for Deep Learning

• Data preparation
  • Acquiring the data
  • Preparing training datasets
  • Preparing test datasets
  • Scaling input variables
  • Utilizing Placeholders and Variables
• Defining the network architecture
• Implementing the Cost Function
• Utilizing the Optimizer
• Applying Initializers
• Fitting the Neural Network
• Constructing the computational graph
  • Inference operations
  • Loss calculation
  • Training operations
• Training the model
  • Graph structure
  • Session management
  • Training loop implementation
• Evaluating model performance
  • Building the evaluation graph
  • Assessing results via evaluation output
• Scaling model training
• Visualizing and evaluating models using TensorBoard

Deep Learning Applications in Anomaly Detection

• Autoencoders
  • Encoder-Decoder architecture
  • Reconstruction loss calculation
• Variational Autoencoders
  • Variational inference techniques
• Generative Adversarial Networks
  • Generator – Discriminator architecture
  • Anomaly Detection (AN) strategies using GANs

Ensemble Frameworks

• Aggregating results from diverse methods
• Bootstrap Aggregating
• Averaging outlier scores