List of Tables

Chapter 1. Building applications for the intelligent web

Table 1.1. A sample dataset to illustrate intelligent-algorithm evaluation

Table 1.2. Performance metrics used in the evaluation of intelligent algorithms

Chapter 3. Recommending relevant content

Table 3.1. Ratings for the users show that Frank and Constantine agree more than Frank and Catherine. This data was modified, with permission, from the MovieLens database.

Chapter 4. Classification: placing things where they belong

Table 4.1. A typical confusion matrix for a simple binary classification problem

Chapter 6. Deep learning and neural networks

Table 6.1. Comparing the output of our perceptron with the output of the logical AND function, which returns 1 if both inputs are equal to 1. Results provided are for the case where w1 = 1, w2 = 1, and w0 = –1.5.

Table 6.2. Input and output values for the XOR function. It outputs a 1 if either x1 or x2 is set to 1 but a 0 of they’re both set to 1 (or both to set to 0).

Chapter 7. Making the right choice

Table 7.1. Considerations of a Bayesian bandit vs. an A/B test. Remember, you should consider your application area and choose the most appropriate solution.