Outline updated November 2026
AI and Modern Machine Learning for Software Developers
Class Duration
35 hours of live training delivered over 5 days.
Student Prerequisites
- Working experience with Python (writing functions, using packages, working with data structures)
- Familiarity with basic data concepts such as tables, CSV files, and JSON
- No prior machine learning experience or advanced mathematics required
Target Audience
Software developers, data analysts, and engineers who want to learn how machine learning works, beyond calling AI APIs. It also suits technical leads, QA engineers testing ML features, and data professionals moving into ML engineering. Teams ready for production-scale ML can continue to Advanced Machine Learning and Data Engineering.
Description
This course covers the machine learning lifecycle in Python, from raw data to a served model. Students prepare data with pandas and Polars and build models with scikit-learn, XGBoost, and LightGBM. They also train neural networks with PyTorch and apply transfer learning with pretrained networks. The datasets are realistic and messy, and models are evaluated honestly and then served with FastAPI and ONNX. All work runs in Google Colab, with AI coding agents helping write and debug code that students then check.
Learning Outcomes
- Choose whether to train a model, reuse a pretrained one, or call a hosted API.
- Prepare datasets by cleaning, encoding, scaling, and splitting them.
- Build leakage-free feature pipelines with scikit-learn.
- Build classification and regression models.
- Evaluate models with appropriate metrics and cross-validation.
- Tune hyperparameters and track experiments with MLflow.
- Cluster data and detect anomalies with unsupervised methods.
- Build and train neural networks with PyTorch.
- Apply transfer learning with pretrained networks.
- Serve models with ONNX export and FastAPI.
- Use AI coding agents to write, debug, and review ML code.
Training Materials
Comprehensive courseware is distributed online at the start of class.
Software Requirements
All hands-on work runs in the free tier of Google Colab, which includes built-in Gemini coding assistance and free GPU access for the deep learning portions. Students need only a Google account and a modern web browser, with no local installation.
Training Topics
Modern Machine Learning Overview
- AI, machine learning, and deep learning
- Supervised, unsupervised, and reinforcement learning
- NumPy, pandas, scikit-learn, and PyTorch
- Custom models, pretrained models, or hosted APIs
- AI coding agents across the lifecycle
Exploring and Understanding Data
- Loading data from files, databases, and APIs
- Exploratory analysis with pandas and Polars
- Distributions, correlations, and target relationships
- Interactive visualization with Plotly
- Missing values, outliers, and duplicates
Preparing Training Data
- Cleaning and imputation strategies
- Encoding categorical variables
- Feature scaling and normalization
- Train, validation, and test splitting
- Class imbalance and resampling techniques
Feature Engineering and Pipelines
- Feature selection and importance measures
- Derived, datetime, and text features
- Dimensionality reduction with PCA
- scikit-learn pipelines and column transformers
- Data leakage causes and prevention
Core Supervised Learning
- Linear and logistic regression families
- Ridge, lasso, and elastic net
- Decision trees and k-nearest neighbors
- Random forests and support vector machines
- Algorithm selection by data size and type
Evaluating Models
- Baseline models and sanity checks
- MAE, RMSE, and R²
- Precision, recall, F1, and ROC-AUC
- Cross-validation strategies
- Error analysis and residual diagnostics
Tuning and Ensembles
- Overfitting and underfitting diagnostics
- Grid, random, and Bayesian hyperparameter search
- XGBoost, LightGBM, and CatBoost
- Model explainability with SHAP
- Experiment tracking with MLflow
Unsupervised Learning
- k-means, DBSCAN, and hierarchical clustering
- Cluster evaluation and selection
- Anomaly and outlier detection
- UMAP and t-SNE for visualization
Neural Networks with PyTorch
- Tensors, autograd, and computational graphs
- Layers, activations, and loss functions
- Training loops, optimizers, and regularization
- Learning curves and failure modes
- GPU acceleration in Colab
Applied Deep Learning and Pretrained Networks
- Convolutional networks for image tasks
- Transfer learning with pretrained torchvision models
- Fine-tuning vs. feature extraction
- Embeddings for search and similarity
Shipping Models: Integration and Serving
- Model persistence and versioning
- ONNX inference from C#, Java, and JavaScript
- Model serving with FastAPI
- Batch vs. real-time inference patterns
- Monitoring, drift, and retraining triggers