How Smart Machines Think by Sean Gerrish

Author:Sean Gerrish
Language: eng
Format: epub
Tags: machine learning; artificial intelligence; ai; ml; neural networks; deep neural networks; deep learning; self driving cars; autonomous vehicles; alphago; reinforcement learning; how ai works; automata; computer vision; search; statistical learning; recommendation engine; autonomous cars; ibm watson; matrix factorization; classification; regression; clustering; overfitting; Netflix grand prize; navigation; computer perception; speech recognition; computer art; darpa grand challenge; search algorithms; search; starcraft bots; computer go; three-layer architecture; imagenet; mechanical turk
Publisher: The MIT Press

OVERFITTING

One of the biggest challenges in fitting neural networks is that if the network is too flexible, or if we don’t have enough data to train the model, then we might learn a model that explains the training examples well but doesn’t generalize to other, unseen examples. We saw this same problem in chapter 6, about the Netflix Prize; this risk is called overfitting. What does overfitting look like in practice?

In figure 9.1a, I show a small sample of data. In this case, it’s just pairs of points, (input, output). Let’s say we want a model for these points that, given an input value, produces an estimate of the output value. This is exactly what you’re doing when you fit a neural network: you’re just fitting a model to predict some output values from the input values. And just below this, in figure 9.1b, is a model I’ve fit to these points. The model is the curvy line that goes through or near many of the points. From this model—the curvy line—you can see what it would predict for each input value, both for the inputs we had seen during training (the black dots) and for many values we hadn’t seen in training.

Figure 9.1

Plots to illustrate overfitting: (a) a sample of points (input, output) for which we hope to build a model; (b) a complex and overfit model of these points (the black curvy line); (c) a linear model of these points (the straight line); and (d) a complex but not overfit model of these points (the black, not-very-curvy line).

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.