Course Outline
Module 1: Core Python for ML Workflows
• Course kickoff and environment setup
Align objectives and establish a reproducible Python ML workspace
• Python language essentials (fast-track)
Review syntax, control flow, functions, and patterns prevalent in ML codebases
• Data structures for ML
Utilize lists, dictionaries, sets, and tuples for features, labels, and metadata
• Comprehensions and functional tools
Implement transformations using comprehensions and higher-order functions
• Object-oriented Python for ML developers
Explore classes, methods, composition, and practical design decisions
• dataclasses and lightweight modelling
Create typed containers for configuration, examples, and results
• Decorators and context managers
Apply timing, caching, logging, and resource-safe execution patterns
• Working with files and paths
Handle robust datasets and serialization formats
• Exceptions and defensive programming
Develop ML scripts that fail safely and transparently
• Modules, packages and project structure
Organize reusable ML codebases effectively
• Typing and code quality
Employ type hints, documentation, and lint-friendly structures
Module 2: Numerical Python, SciPy and Data Handling
• NumPy foundations for vectorised computing
Master efficient array operations and performance-aware coding
• Indexing, slicing, broadcasting and shapes
Ensure safe tensor manipulation and shape reasoning
• Linear algebra essentials with NumPy and SciPy
Perform stable matrix operations and decompositions used in ML
• SciPy deep dive
Explore statistics, optimisation, curve fitting, and sparse matrices
• Pandas for tabular ML data
Clean, join, aggregate, and prepare datasets
• scikit-learn deep dive
Understand the estimator interface, pipelines, and reproducible workflows
• Visualisation essentials
Create diagnostic plots for data exploration and model behaviour analysis
Module 3: Programming Patterns for Building ML Applications
• From notebook to maintainable project
Refactor exploratory code into structured packages
• Configuration management
Manage externalised parameters and implement startup validation
• Logging, warnings and observability
Implement structured logging for debuggable ML systems
• Reusable components with OOP and composition
Design extensible transformers and predictors
• Practical design patterns
Apply Pipeline, Factory or Registry, Strategy, and Adapter patterns
• Data validation and schema checks
Prevent silent data issues through rigorous validation
• Performance and profiling
Identify bottlenecks and apply optimisation techniques
• Model I O and inference interfaces
Ensure safe persistence and clean prediction interfaces
• End-to-end mini build
Construct a production-style ML pipeline with configuration and logging
Module 4: Statistical Learning for Tabular, Text and Image
• Evaluation foundations
Manage train and validation splits, ensure honest cross-validation, and align with business metrics
• Advanced tabular ML
Utilize regularised GLMs, tree ensembles, and leakage-free preprocessing
• Calibration and uncertainty
Apply Platt scaling, isotonic regression, bootstrap, and conformal prediction
• Classical NLP methods
Understand tokenisation trade-offs, TF-IDF, linear models, and Naive Bayes
• Topic modelling
Explore LDA fundamentals and practical limitations
• Classical computer vision
Implement HOG, PCA, and feature-based pipelines
• Error analysis
Detect bias, label noise, and spurious correlations
• Hands-on labs
Leakage-proof tabular pipeline
Text baseline comparison and interpretation
Classical vision baseline with structured failure analysis
Module 5: Neural Networks for Tabular, Text and Image
• Training loop mastery
Develop clean PyTorch loops with AMP, clipping, and reproducibility
• Optimisation and regularisation
Master initialisation, normalisation, optimisers, and schedulers
• Mixed precision and scaling
Implement gradient accumulation and checkpointing strategies
• Tabular neural networks
Use categorical embeddings, feature crosses, and ablation studies
• Text neural networks
Work with embeddings, CNNs, BiLSTM or GRU, and sequence handling
• Vision neural networks
Understand CNN fundamentals and ResNet-style architectures
• Hands-on labs
Reusable training framework
Tabular NN vs boosting comparison
CNN with augmentation and scheduling experiments
Module 6: Advanced Neural Architectures
• Transfer learning strategies
Employ freeze and unfreeze patterns and discriminative learning rates
• Transformer architectures for text
Explore self-attention internals and fine-tuning approaches
• Vision backbones and dense prediction
Understand ResNet, EfficientNet, Vision Transformers, and U-Net concepts
• Advanced tabular architectures
Explore TabTransformer, FT-Transformer, and Deep and Cross networks
• Time series considerations
Manage temporal splits and detect covariate shift
• PEFT and efficiency techniques
Navigate LoRA, distillation, and quantisation trade-offs
• Hands-on labs
Fine-tuning pretrained text transformer
Fine-tuning pretrained vision model
Tabular transformer vs GBDT comparison
Module 7: Generative AI Systems
• Prompting fundamentals
Implement structured prompting and controlled generation
• LLM foundations
Understand tokenisation, instruction tuning, and hallucination mitigation
• Retrieval-Augmented Generation
Master chunking, embeddings, hybrid search, and evaluation metrics
• Fine-tuning strategies
Apply LoRA and QLoRA with data quality controls
• Diffusion models
Grasp latent diffusion intuition and practical adaptation
• Synthetic tabular data
Utilize CTGAN and address privacy considerations
• Hands-on labs
Production-style RAG mini-application
Structured output validation with schema enforcement
Optional diffusion experimentation
Module 8: AI Agents and MCP
• Agent loop design
Implement observe, plan, act, reflect, and persist cycles
• Agent architectures
Explore ReAct, plan-and-execute, and multi-agent coordination
• Memory management
Utilize episodic, semantic, and scratchpad approaches
• Tool integration and safety
Establish tool contracts, sandboxing, and prompt injection defences
• Evaluation frameworks
Create replayable traces, task suites, and regression testing protocols
• MCP and protocol-based interoperability
Design MCP servers with secure tool exposure
• Hands-on labs
Build an agent from scratch
Expose tools via MCP-style server
Create evaluation harness with safety constraints
Requirements
Participants should possess a working knowledge of Python programming.
This programme is designed for intermediate to advanced technical professionals.
Testimonials (2)
the ML ecosystem not only MLFlow but Optuna, hyperops, docker , docker-compose
Guillaume GAUTIER - OLEA MEDICAL
Course - MLflow
I enjoyed participating in the Kubeflow training, which was held remotely. This training allowed me to consolidate my knowledge for AWS services, K8s, all the devOps tools around Kubeflow which are the necessary bases to properly tackle the subject. I wanted to thank Malawski Marcin for his patience and professionalism for training and advice on best practices. Malawski approaches the subject from different angles, different deployment tools Ansible, EKS kubectl, Terraform. Now I am definitely convinced that I am going into the right field of application.
