Cargando…
How Smart Machines Think /
The future is here: Self-driving cars are on the streets, an algorithm gives you movie and TV recommendations, IBM's Watson triumphed on Jeopardy over puny human brains, computer programs can be trained to play Atari games. But how do all these thingswork? In this book, Sean Gerrish offers an e...
| Autor principal: | |
|---|---|
| Otros Autores: | |
| Formato: | Electrónico eBook |
| Idioma: | Inglés |
| Publicado: |
Cambridge, MA :
The MIT Press,
[2018]
|
| Colección: | Book collections on Project MUSE.
|
| Temas: | |
| Acceso en línea: | Texto completo |
Tabla de Contenidos:
- 1. The Secret of the Automaton; The Flute Player; Today's Automata; The Swing of a Pendulum; Automata We'll Discuss in this Book; 2. Self-Driving Cars and the DARPA Grand Challenge; The 1 Million Race in the Desert; How to Build a Self-Driving Car; Planning a Path; Path Search; Navigation; The Winner of the Grand Challenge; A Failed Race; 3. Keeping within the Lanes: Perception in Self-Driving Cars; The Second Grand Challenge; Machine Learning in Self-Driving Cars; Stanley's Architecture; Avoiding Obstacles; Finding the Road's Edges Seeing the RoadPath Planning; How Parts of Stanley's Brain Talked to Each Other; 4. Yielding at Intersections: The Brain of a Self-Driving Car; The Urban Challenge; Perceptual Abstraction; The Race; Boss's Higher-Level Reasoning Layer; Getting Past Traffic Jams; Three-Layer Architectures; Classifying the Objects Seen by Self-Driving Cars; Self-Driving Cars are Complicated Systems; The Trajectory of Self-Driving Cars; 5. Netflix and the Recommendation-Engine Challenge; A Million-Dollar Grand Prize; The Contenders; How to Train a Classifier; The Goals of the Competition; A Giant Ratings Matrix Matrix FactorizationThe First Year Ends; 6. Ensembles of Teams: The Netflix Prize Winners; Closing the Gap between Contenders; The End of the First Year; Predictions Over Time; Overfitting; Model Blending; The Second Year; The Final Year; After the Competition; 7. Teaching Computers by Giving Them Treats; DeepMind Plays Atari; Reinforcement Learning; Instructions to the Agent; Programming the Agent; How the Agent Sees the World; Nuggets of Experience; Playing Atari with Reinforcement Learning; 8. How to Beat Atari Games by Using Neural Networks; Neural Information Processing Systems Approximation, Not PerfectionNeural Networks as Mathematical Functions; The Architecture of an Atari-Playing Neural Network; Digging Deeper into Neural Networks; 9. Artificial Neural Networks' View of the World; The Mystique of Artificial Intelligence; The Automaton Chess Player, or the Turk; Misdirection in Neural Networks; Recognizing Objects in Images; Overfitting; ImageNet; Convolutional Neural Networks; Why "Deep" Networks?; Data Bottlenecks; 10. Looking Under the Hood of Deep Neural Networks; Computer-Generated Images; Squashing Functions; ReLU Activation Functions; Android Dreams 11. Neural Networks that Can Hear, Speak, and RememberWhat It Means for a Machine to "Understand"; Deep Speech II; Recurrent Neural Networks; Generating Captions for Images; Long Short-Term Memory; Adversarial Data; 12. Understanding Natural Language (and Jeopardy! Questions); Publicity Stunt or Boon to AI Research?; IBM Watson; Challenges in Beating Jeopardy; Long Lists of Facts; The Jeopardy Challenge is Born; DeepQA; Question Analysis; How Watson Interprets a Sentence; 13. Mining the Best Jeopardy! Answer; The Basement Baseline; Candidate Generation; Searching for Answers