The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our WorldBasic Books, 2015/09/22 - 352 ページ Recommended by Bill Gates A thought-provoking and wide-ranging exploration of machine learning and the race to build computer intelligences as flexible as our own In the world's top research labs and universities, the race is on to invent the ultimate learning algorithm: one capable of discovering any knowledge from data, and doing anything we want, before we even ask. In The Master Algorithm, Pedro Domingos lifts the veil to give us a peek inside the learning machines that power Google, Amazon, and your smartphone. He assembles a blueprint for the future universal learner--the Master Algorithm--and discusses what it will mean for business, science, and society. If data-ism is today's philosophy, this book is its bible. |
目次
| 1 | |
The Master Algorithm | 23 |
Humes Problem of Induction | 57 |
How Does Your Brain Learn? | 93 |
Evolution Natures Learning Algorithm | 121 |
In the Church of the Reverend Bayes | 143 |
You Are What You Resemble | 177 |
他の版 - すべて表示
多く使われている語句
Alchemy analogizers attributes autoencoder backprop Bayesian networks better big data brain called cancer cell Chapter chunking clusters combine complex concepts connectionists curve database decision tree diagnose drugs e-mail encode engineering entities everything evolution evolutionaries evolve example exponential Facebook figure flip function genes genetic algorithm genetic programming genome Google gradient descent human hypotheses images inference input intelligence interact invented inverse deduction knowledge layer learning algorithms look machine learning Markov chain Markov logic Markov networks Master Algorithm match million multilayer perceptron Naïve Bayes nearest-neighbor Netflix neural networks neurons optimization output overfitting parameters patients predict probabilistic probability problem random reinforcement learning result rithm Robby robot scientists set of rules similar solve spam statistical step structure support vector SVMs symbolists theorem theory there’s things tion turn universal learner variables weights