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

Introduction to Applied Machine Learning

• Comparison of statistical learning and machine learning
• Iteration and evaluation processes
• The Bias-Variance trade-off
• Distinctions between Supervised and Unsupervised Learning
• Problems addressed through Machine Learning
• Train, Validation, and Test – The ML workflow for preventing overfitting
• The general Machine Learning workflow
• Overview of machine learning algorithms
• Selecting the most suitable algorithm for a given problem

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
  • The challenge of unbalanced classes
• Visualizing model performance
  • Profit curve
  • ROC curve
  • Lift curve
• Model selection techniques
• Model tuning using grid search strategies

Data Preparation for Modelling

• Data import and storage techniques
• Understanding the data through basic exploration
• Data manipulation using the pandas library
• Data transformations and wrangling
• Exploratory data analysis
• Handling missing observations – detection and solutions
• Managing outliers – detection and 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 and nature of Neural Networks
• Comparing Neural Networks with Regression Models
• Understanding the 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 in this context
• Learning about Feedforward and Feedback Neural Networks
• Understanding Forward Propagation and Back Propagation

Building Simple Deep Learning Models with Keras

• Creating a Keras model
• Analyzing and understanding the data
• Defining the Deep Learning model structure
• Compiling the model
• Fitting the model to the data
• Handling classification data
• Working with classification models
• Utilizing the trained models

Working with TensorFlow for Deep Learning

• Data preparation
  • Downloading datasets
  • Preparing training data
  • Preparing test data
  • Scaling input values
  • Utilizing Placeholders and Variables
• Defining the network architecture
• Implementing the Cost Function
• Applying the Optimizer
• Using Initializers
• Fitting the Neural Network
• Constructing the computation graph
  • Inference
  • Loss calculation
  • Training process
• Training the model
  • Graph structure
  • Session management
  • Training loop implementation
• Evaluating the model
  • Building the evaluation graph
  • Assessing performance with evaluation outputs
• Training models at scale
• Visualizing and evaluating models using TensorBoard

Application of Deep Learning in Anomaly Detection

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

Ensemble Frameworks

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