/MachineLearning-QandAI-book

Machine Learning Q and AI book

Primary LanguageJupyter NotebookBSD 3-Clause "New" or "Revised" LicenseBSD-3-Clause

Machine Learning and AI Beyond the Basics Book

The Supplementary Materials for the Machine Learning Q and AI book by Sebastian Raschka.

Please use the Discussions for any questions about the book!

2023-ml-qai-cover


About the Book

If you’ve locked down the basics of machine learning and AI and want a fun way to address lingering knowledge gaps, this book is for you. This rapid-fire series of short chapters addresses 30 essential questions in the field, helping you stay current on the latest technologies you can implement in your own work.

Each chapter of Machine Learning Q and AI asks and answers a central question, with diagrams to explain new concepts and ample references for further reading

  • Multi-GPU training paradigms
  • Finetuning transformers
  • Differences between encoder- and decoder-style LLMs
  • Concepts behind vision transformers
  • Confidence intervals for ML
  • And many more!

This book is a fully edited and revised version of Machine Learning Q and AI, which was available on Leanpub.


Reviews

“One could hardly ask for a better guide than Sebastian, who is, without exaggeration, the best machine learning educator currently in the field. On each page, Sebastian not only imparts his extensive knowledge but also shares the passion and curiosity that mark true expertise.”
-- Chris Albon, Director of Machine Learning, The Wikimedia Foundation


Links



Table of Contents

Title URL Link Supplementary Code
1 Embeddings, Representations, and Latent Space
2 Self-Supervised Learning
3 Few-Shot Learning
4 The Lottery Ticket Hypothesis
5 Reducing Overfitting with Data
6 Reducing Overfitting with Model Modifications
7 Multi-GPU Training Paradigms
8 The Keys to the Success of Transformers
9 Generative AI Models
10 Sources of Randomness data-sampling.ipynb
dropout.ipynb
random-weights.ipynb
PART II: COMPUTER VISION
11 Calculating the Number of Parameters conv-size.ipynb
12 The Equivalence of Fully Connected and Convolutional Layers fc-cnn-equivalence.ipynb
13 Large Training Sets for Vision Transformers
PART III: NATURAL LANGUAGE PROCESSING
14 The Distributional Hypothesis
15 Data Augmentation for Text backtranslation.ipynb
noise-injection.ipynb
sentence-order-shuffling.ipynb
synonym-replacement.ipynb
synthetic-data.ipynb
word-deletion.ipynb
word-position-swapping.ipynb
16 “Self”-Attention
17 Encoder- And Decoder-Style Transformers
18 Using and Finetuning Pretrained Transformers
19 Evaluating Generative Large Language Models BERTScore.ipynb
bleu.ipynb
perplexity.ipynb
rouge.ipynb
PART IV: PRODUCTION AND DEPLOYMENT
20 Stateless And Stateful Training
21 Data-Centric AI
22 Speeding Up Inference
23 Data Distribution Shifts
PART V: PREDICTIVE PERFORMANCE AND MODEL EVALUATION
24 Poisson and Ordinal Regression
25 Confidence Intervals four-methods.ipynb
four-methods-vs-true-value.ipynb
26 Confidence Intervals Versus Conformal Predictions conformal_prediction.ipynb
27 Proper Metrics
28 The K in K-Fold Cross-Validation
29 Training and Test Set Discordance
30 Limited Labeled Data