Deep Learning Basics with TensorFlow and Keras
A responsible TensorFlow/Keras portfolio with tensors, data pipelines, model APIs, training, diagnostics, vision, text, export, and a capstone model card.
What you will be able to do
A responsible TensorFlow/Keras portfolio with tensors, data pipelines, model APIs, training, diagnostics, vision, text, export, and a capstone model card.
Use a repeatable workflow instead of disconnected tips.
Check assumptions, evidence, output quality, and limitations before using results.
Create a capstone artifact that can be inspected, improved, and reviewed.
What you need before starting
Learners who have completed the technical ML sequence and want their first deep learning workflow.
Applied Machine Learning Algorithms is strongly recommended.
Static lessons, activities, knowledge checks, learner templates, and a downloadable text-first pack.
12-module course sequence
The sequence follows the approved detailed syllabus and is implemented as a complete text-first shell.
TensorFlow, Keras, and the Course Setup
- help learners understand the TensorFlow/Keras ecosystem and set up a small reliable workflow.
- Text-first module with units, activity, knowledge check, and summary.
Tensors, Shapes, and TensorFlow Data
- make learners fluent with TensorFlow tensors and input pipelines.
- Text-first module with units, activity, knowledge check, and summary.
Keras Model APIs
- teach the main Keras ways to define models.
- Text-first module with units, activity, knowledge check, and summary.
Compile, Fit, Metrics, and Validation
- make the standard Keras training workflow clear.
- Text-first module with units, activity, knowledge check, and summary.
Callbacks, Checkpoints, and TensorBoard
- teach experiment discipline before larger models.
- Text-first module with units, activity, knowledge check, and summary.
Regularization and Training Diagnostics
- teach why Keras models fail and how to repair them carefully.
- Text-first module with units, activity, knowledge check, and summary.
Computer Vision with Keras
- introduce image classification through small understandable models.
- Text-first module with units, activity, knowledge check, and summary.
Transfer Learning and Fine-Tuning
- show how pretrained Keras models change the workflow.
- Text-first module with units, activity, knowledge check, and summary.
Text, Tokenization, and Embeddings
- introduce text workflows without jumping straight to large language models.
- Text-first module with units, activity, knowledge check, and summary.
Transformer Workflows and Pretrained Models
- teach practical transformer use while keeping claims honest.
- Text-first module with units, activity, knowledge check, and summary.
Saving, Export, and Responsible Use
- teach what a saved model is and what production readiness still requires.
- Text-first module with units, activity, knowledge check, and summary.
Capstone TensorFlow/Keras Portfolio
- bring the course together into a responsible final project.
- Text-first module with units, activity, knowledge check, and summary.
Course status: outline published, lessons in development
The full syllabus, module structure, activities, and download pack are published and free to use now. Detailed lesson writing is still in progress, so lesson pages currently give the shape of each topic rather than the final teaching depth. Per-module assessments, worked examples, instructional diagrams, and external specialist review are planned next.