Setting up a secure Ubuntu LAMP server has an amazing article. However, it is a little outdated: UFW: In case VPS kicks you out even though you have allowed SSH port: [How to] Configures Iptables with INPUT rules (with dynamic NBD). Apache2: You should find 000-default site instead of default. All the site configuration should be ended by […]

# Month: June 2016

## Learning From Data – A Short Course: Exercise 5.5

Page 176: Assume we set aside 100 examples from D that will not be used in training, but will be used to select one of three final hypotheses , , produced by three different learning algorithms that train on the rest on the data. Each algorithm works with a different of size 500. We would […]

## Learning From Data – A Short Course: Exercise 5.4

Page 174: Consider the following approach to learning. By looking at the data, it appears that the data is linearly separable, so we go ahead and use a simple perceptron, and get a training error of zero after determining the optimal set of weights. We now wish to make some generalization conclusions, so we look […]

## Learning From Data – A Short Course: Exercise 5.3

Page 172: In an experiment to determine the distribution of sizes of fish in a lake, a net might be used to catch a representative sample of fish. The sample is then analyzed to find out the fractions of fish of different sizes. If the sample is big enough, statistical conclusions may be drawn about […]

## Backward Chaining implementation as State Space Search problem

To me, Backward Chaining implementation can be viewed as a state space search problem. In this problem, a state consists two components: (Path, Goals) Path is the list of ordered rules that are used. Goals is the set of facts that currently need to be deduced. An available action at a state is a applicable […]

## Learning From Data – A Short Course: Exercise 5.2

Page 170: Suppose that for 5 weeks in a row, a letter arrives in the mail that predicts the outcome of the upcoming Monday night football game. You keenly watch each Monday and to your surprise, the prediction is correct each time. On the day after the fifth game, a letter arrives, stating that if […]

## Learning From Data – A Short Course: Exercise 5.1

Consider hypothesis sets and that contain Boolean functions on 10 Boolean variables, so . contains all Boolean functions which evaluate to +1 on exactly one input point, and to elsewhere; contains all Boolean functions which evaluate to +1 on exactly 100 input points, and to -1 elsewhere. (a) How big (number of hypotheses) are and […]