Course Outline
Module 1: Core Python for Machine Learning Workflows
• Course orientation and environment configuration
Aligning instructional objectives and establishing a reproducible Python workspace for machine learning tasks
• Python language fundamentals (expedited review)
Reviewing syntax, control flow, functions, and coding patterns frequently encountered in machine learning codebases
• Data structures tailored for machine learning
Utilizing lists, dictionaries, sets, and tuples to manage features, labels, and metadata
• List comprehensions and functional utilities
Implementing data transformations using comprehensions and higher-order functions
• Object-oriented Python for machine learning developers
Applying classes, methods, composition, and practical design decisions
• dataclasses and lightweight data modelling
Creating typed containers for configuration parameters, data examples, and result sets
• Decorators and context managers
Implementing timing, caching, logging, and resource-safe execution patterns
• File and path management
Ensuring robust dataset handling and managing serialization formats
• Exception handling and defensive programming
Developing machine learning scripts that fail safely and transparently
• Modules, packages, and project architecture
Organizing reusable machine learning codebases
• Type hinting and code quality standards
Incorporating type hints, documentation, and lint-friendly structure
Module 2: Numerical Python, SciPy, and Data Processing
• NumPy foundations for vectorized computation
Executing efficient array operations and performance-aware coding practices
• Indexing, slicing, broadcasting, and shape management
Performing safe tensor manipulation and shape reasoning
• Linear algebra essentials with NumPy and SciPy
Applying stable matrix operations and decompositions utilized in machine learning
• Advanced SciPy applications
Covering statistics, optimization, curve fitting, and sparse matrices
• Pandas for tabular machine learning data
Cleaning, joining, aggregating, and preparing datasets for analysis
• scikit-learn in-depth analysis
Utilizing the estimator interface, pipelines, and reproducible workflows
• Visualization essentials
Generating diagnostic plots for data exploration and model behavior assessment
Module 3: Programming Patterns for Building Machine Learning Applications
• Transitioning from notebooks to maintainable projects
Refactoring exploratory code into structured packages
• Configuration management
Managing externalized parameters and startup validation
• Logging, warnings, and observability
Implementing structured logging for debuggable machine learning systems
• Reusable components via OOP and composition
Designing extensible transformers and predictors
• Applied design patterns
Implementing Pipeline, Factory or Registry, Strategy, and Adapter patterns
• Data validation and schema verification
Preventing silent data integrity issues
• Performance analysis and profiling
Identifying bottlenecks and applying optimization techniques
• Model Input/Output and inference interfaces
Ensuring safe persistence and clean prediction interfaces
• End-to-end mini-project construction
Developing a production-style machine learning pipeline with configuration and logging
Module 4: Statistical Learning for Tabular, Text, and Image Data
• Evaluation foundations
Implementing train and validation splits, honest cross-validation, and business-aligned metrics
• Advanced tabular machine learning
Applying regularized GLMs, tree ensembles, and leakage-free preprocessing
• Calibration and uncertainty quantification
Using Platt scaling, isotonic regression, bootstrap, and conformal prediction
• Classical NLP methods
Addressing tokenization trade-offs, TF-IDF, linear models, and Naive Bayes
• Topic modelling
Exploring LDA fundamentals and practical limitations
• Classical computer vision
Applying HOG, PCA, and feature-based pipelines
• Error analysis
Detecting bias, label noise, and spurious correlations
• Practical laboratory exercises
Implementing a leakage-proof tabular pipeline
Conducting text baseline comparison and interpretation
Executing a classical vision baseline with structured failure analysis
Module 5: Neural Networks for Tabular, Text, and Image Data
• Mastery of training loops
Implementing clean PyTorch loops with AMP, clipping, and reproducibility
• Optimization and regularization
Managing initialization, normalization, optimizers, and schedulers
• Mixed precision and scaling strategies
Applying gradient accumulation and checkpointing strategies
• Tabular neural networks
Utilizing categorical embeddings, feature crosses, and ablation studies
• Text neural networks
Applying embeddings, CNNs, BiLSTM or GRU, and sequence handling
• Vision neural networks
Implementing CNN fundamentals and ResNet-style architectures
• Practical laboratory exercises
Developing a reusable training framework
Comparing tabular NN against boosting methods
Conducting CNN experiments with augmentation and scheduling
Module 6: Advanced Neural Architectures
• Transfer learning strategies
Applying freeze and unfreeze patterns, and discriminative learning rates
• Transformer architectures for text
Analyzing self-attention internals and fine-tuning approaches
• Vision backbones and dense prediction
Examining ResNet, EfficientNet, Vision Transformers, and U-Net concepts
• Advanced tabular architectures
Implementing TabTransformer, FT-Transformer, and Deep and Cross networks
• Time series considerations
Addressing temporal splits and covariate shift detection
• PEFT and efficiency techniques
Evaluating LoRA, distillation, and quantization trade-offs
• Practical laboratory exercises
Fine-tuning a pretrained text transformer
Fine-tuning a pretrained vision model
Comparing tabular transformers against GBDT
Module 7: Generative AI Systems
• Prompting fundamentals
Implementing structured prompting and controlled generation
• LLM foundations
Addressing tokenization, instruction tuning, and hallucination mitigation
• Retrieval-Augmented Generation (RAG)
Managing chunking, embeddings, hybrid search, and evaluation metrics
• Fine-tuning strategies
Applying LoRA and QLoRA with data quality controls
• Diffusion models
Understanding latent diffusion intuition and practical adaptation
• Synthetic tabular data
Implementing CTGAN and addressing privacy considerations
• Practical laboratory exercises
Developing a production-style RAG mini-application
Validating structured output with schema enforcement
Conducting optional diffusion experimentation
Module 8: AI Agents and MCP
• Agent loop design
Implementing observe, plan, act, reflect, and persist cycles
• Agent architectures
Applying ReAct, plan-and-execute, and multi-agent coordination
• Memory management
Utilizing episodic, semantic, and scratchpad approaches
• Tool integration and safety
Defining tool contracts, sandboxing, and prompt injection defenses
• Evaluation frameworks
Implementing replayable traces, task suites, and regression testing
• MCP and protocol-based interoperability
Designing MCP servers with secure tool exposure
• Practical laboratory exercises
Constructing an agent from scratch
Exposing tools via an MCP-style server
Creating an evaluation harness with safety constraints
Requirements
Participants are expected to possess a working proficiency in Python programming.
This programme is designed for intermediate to advanced technical professionals engaged in public sector operations.
Testimonials (3)
I really liked the end where we took the time to play around with CHAT GPT. The room was not set up the best for this- instead of one large table a couple of small ones so we could get into small groups and brainstorm would have helped
Nola - Laramie County Community College
Course - Artificial Intelligence (AI) Overview
Working from first principles in a focused way, and moving to applying case studies within the same day
Maggie Webb - Department of Jobs, Regions, and Precincts
Course - Artificial Neural Networks, Machine Learning, Deep Thinking
That it was applying real company data. Trainer had a very good approach by making trainees participate and compete
