The Little Learner

A Straight Line to Deep Learning

by Friedman, Mendhekar

| ISBN: 9780262375931 | Copyright 2023

Click here to preview

Instructor Requests

Print Desk Copy Ancillaries

A highly accessible, step-by-step introduction to deep learning, written in an engaging, question-and-answer style.

The Little Learner introduces deep learning from the bottom up, inviting students to learn by doing. With the characteristic humor and Socratic approach of classroom favorites The Little Schemer and The Little Typer, this kindred text explains the workings of deep neural networks by constructing them incrementally from first principles using little programs that build on one another. Starting from scratch, the reader is led through a complete implementation of a substantial application: a recognizer for noisy Morse code signals. Example-driven and highly accessible, The Little Learner covers all of the concepts necessary to develop an intuitive understanding of the workings of deep neural networks, including tensors, extended operators, gradient descent algorithms, artificial neurons, dense networks, convolutional networks, residual networks, and automatic differentiation.

•Conversational style, illustrations, and question-and-answer format make deep learning accessible and fun
•Incremental approach constructs advanced concepts from first principles
•Presents key ideas of machine learning using a small, manageable subset of the Scheme language
•Suitable for anyone with knowledge of high school math and some programming experience

Expand/Collapse All
Contents (pg. ix)
Foreword by Guy L. Steele Jr. (pg. xi)
Foreword by Peter Norvig (pg. xiii)
Preface (pg. xix)
Transcribing to Scheme (pg. xxiii)
0. Are You Schemish? (pg. 2)
1. The Lines Sleep Tonight (pg. 18)
2. The More We Learn, the Tenser We Become (pg. 30)
Interlude I. The More We Extend, the Less Tensor We Get (pg. 46)
3. Running Down a Slippery Slope (pg. 56)
4. Slip-slidin’ Away (pg. 72)
Interlude II. Too Many Toys Make Us Hyperactive (pg. 92)
5. Target Practice (pg. 98)
Interlude III. The Shape of Things to Come (pg. 112)
6. An Apple a Day (pg. 116)
7. The Crazy “ates” (pg. 130)
8. The Nearer Your Destination, the Slower You Become (pg. 144)
Interlude IV. Smooth Operator (pg. 154)
9. Be Adamant (pg. 162)
Interlude V. Extensio Magnifico! (pg. 176)
10. Doing the Neuron Dance (pg. 194)
11. In Love with the Shape of Relu (pg. 212)
12. Rock Around the Block (pg. 236)
13. An Eye for an Iris (pg. 250)
Interlude VI. How the Model Trains (pg. 270)
Interlude VII. Are Your Signals Crossed? (pg. 282)
14. It’s Really Not That Convoluted . . . (pg. 298)
15. . . . But It Is Correlated! (pg. 320)
Epilogue. We’ve Only Just Begun (pg. 342)
Appendix A. Ghost in the Machine (pg. 350)
Appendix B. I Could Have Raced All Day (pg. 374)
Acknowledgments (pg. 399)
References (pg. 401)
Index (pg. 402)

Daniel P. Friedman

Daniel P. Friedman is Professor of Computer Science in the School of Informatics, Computing, and Engineering at Indiana University and is the author of many books published by the MIT Press, including The Little Schemer and The Seasoned Schemer (with Matthias Felleisen); The Little Prover (with Carl Eastlund); and The Reasoned Schemer (with William E. Byrd, Oleg Kiselyov, and Jason Hemann).

Anurag Mendhekar

Anurag Mendhekar is Cofounder and President of Paper Culture, where he focuses on developing artificial intelligence for creativity, and an entrepreneur. He started his career at Xerox´ s Palo Alto Research Center (PARC), where he was one of the inventors of aspect-oriented programming.