TensorFlow basics to seq2seq, one chapter per folder

What it does This is the official code repository for the book Machine Learning with TensorFlow. It stores Jupyter notebooks organized by chapter, covering everything from defining tensors and linear regression to convolutional networks, sequence-to-sequence models, and image ranking. The README makes clear that explanations live in the book itself; this is strictly the accompanying code.

The interesting bit The curriculum feels like a deliberate tour through a full graduate syllabus rather than a grab bag of trendy architectures. You get Hidden Markov Models and self-organizing maps sitting next to CNNs and RNNs—topics that now feel vintage but still round out a solid foundation.

Key highlights

• Eleven chapters of notebooks spanning basics to advanced models.
• Unusually broad coverage includes RankNet, Viterbi decode, and denoising autoencoders alongside standard deep learning fare.
• Folder structure mirrors the book exactly, with concepts labeled sequentially per chapter.
• Covers foundational TensorFlow mechanics including Interactive session, Session loggings, and variable save/load cycles.

Caveats

• The README is strictly a table of contents; step-by-step explanations require owning the textbook.
• Prominently features session-based concepts (Interactive session, Session loggings, evaluating ops) that predate modern TensorFlow conventions.

Verdict Useful if you own the book or want a structured, broad archive of textbook ML implementations. Less useful as a standalone reference or if you need code aligned with current TensorFlow patterns.