Topics Covered

• Predictive AI Business and Technology Drivers
• Predictive AI Benefits
• Common Risks and Challenges of Using Predictive AI
• Business Problem Categories Addressed by AI
• Types of Predictive AI
• Common Predictive AI Learning Approaches
• Understanding Predictive AI Learning and Model Training
• Step-by-Step Training Loop Process

• Supervised Learning, Unsupervised Learning, Continuous Learning
• Heuristic Learning, Semi-Supervised Learning, Reinforcement Learning
• Common Predictive AI Functional Designs, Computer Vision, Pattern Recognition
• Robotics, Natural Language Processing (NLP)
• Speech Recognition, Natural Language Understanding (NLU)
• Understanding AI Models and Neural Networks

Topics Covered

• Understanding Supervised Learning
• Understanding Unsupervised Learning
• Essential Analytics Techniques and Processes
• Introduction to Feature Encoding and Feature Imputation
• Introduction to Dimensionality Reduction

• Introduction to Data Wrangling
• Introduction to Model Evaluation and Training Performance Evaluation
• Introduction to Baseline Modeling and Model Optimization
• Introduction to Overfitting Avoidance
• Introduction to Transfer Learning

Topics Covered

• Predictive AI Model Selection and Hyperparameter Tuning
• Predictive AI Model Deployment, Monitoring and Maintenance
• Predictive AI Bias Detection and Mitigation
• Predictive AI Model Explainability and Interpretability
• Predictive AI Model Evaluation and Validation Techniques
• Data Preprocessing Techniques, Overfitting and Regularization
• Performance Optimization Techniques for Predictive AI Models

• Understanding Predictive Neural Networks and Models
• Neural Network Types, Neurons, Layers, Links, Weights
• Loss, Hyperparameters, Learning Rate, Bias, Epoch
• Activation Functions (Sigmoid, Tanh, ReLU, Leaky ReLU, Softmax,
  Softplus)
• Neuron Cell Types (Input, Backfed, Noisy, Hidden, Probabilistic,
  Spiking, Recurrent, Memory, Kernel, Convolution, Pool, Output,
  Match Input, etc.)
• Common Neural Network Architectures for Predictive AI Systems

Topics Covered

• Data Wrangling Patterns for Preparing Data for Predictive Neural Network Input
• Feature Encoding for Converting Categorical Features
• Feature Imputation for Inferring Feature Values
• Feature Scaling for Training Datasets with Broad Features
• Text Representation for Converting Data while Preserving Semantic and Syntactic Properties
• Dimensionality Reduction to Reduce Feature Space for Predictive Neural Network Input
• Supervised Learning Patterns for Training Neural Network Models
• Supervised Network Configuration for Establishing the Number of Neurons in Network Layers
• Image Identification for using a Convolutional Pattern Neural Network
• Sequence Identification for using a Long Short Term Memory Neural Network
• Unsupervised Learning Patterns for Training Pattern Neural Network Models

• Pattern Identification for Visually Identifying Patterns via a Self Organizing Map
• Content Filtering for Producing Recommendations
• Model Evaluation Patterns for Measuring Predictive Neural Network Performance
• Training Performance Evaluation for Assessing Predictive Neural Network Performance
• Prediction Performance Evaluation for Predictive Neural Networks in Production
• Baseline Modeling for Assessing and Comparing Complex Predictive Neural Networks
• Model Optimization Patterns for Refining and Adapting Predictive Neural Networks
• Overfitting Avoidance for Tuning a Predictive Neural Network
• Frequent Model Retraining for Keeping a Neural Network in Synch with Current Data
• Transfer Learning for Accelerating Predictive Neural Network Training

Topics Covered