The Little Learner A Straight Line to Deep Learning

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

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 is cofounder and president of Paper Culture and an entrepreneur focusing on artificial intelligence for creativity and the delivery of VR video over the Internet. He started his career at Xerox´s Palo Alto Research Center (PARC), where he was one of the inventors of Aspect Oriented Programming.

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