Machine Learning (part of exam 2/3) Flashcards
(48 cards)
Why can it be useful for a machine to learn?
- it’s essential for unknown environments (ie when the designer isn’t omniscent)
- it’s useful as a system construction method (ie expose the agent to reality rather than trying to write down reality)
Assign the correct names to the following quotes:
- Learning is making useful changes in our minds.
- Learning denotes changes in the system that […] enable the system to do the same task or tasks drawn from the same population more efficiently and more effectively the next time.
- Learning is constructing or modifying representations of what is being experienced.
- Minsky
- Simon
- Michalski
What is Mitchell’s definition of Machine Learning (1997)?
A computer program is said to learn from experience E with respect to some class of task T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.
What information needs to be given in order to reach the goal of improving the performance on a task?
- a task T
- a performance measure P
- some experience E
On the example of teaching a machine to play Backgammon, what are the task T, the performance measure P and the experience E?
- T: play backgammon
- P: percentage of games won
- E: previously played games
What examples have we learned where machine learning is used in our daily life?
- teaching machines to play games
- regognizing spam-Mail
- handwritten character recognition
- classifying stars, galaxies, quasrs,..
- market basket analysis (recommendation systems, store layouts)
On the example of Spam-Mail, what are the task T, the performance measure P and the experience E?
- T: sort E-Mails into categories
- P: weighted sum of mistakes (letting spam through is weighted less than misclassifying regular E-Mails as spam)
- E: handsorted E-Mails by user
What’s the name of the learning method most spam-filters use to teach their machines to recognize spam mails?
Bayesian Learning
On the example of Handwritten Character Recognition, what are the task T, the performance measure P and the experience E?
- T: recognize a handwritten character
- P: recognition rate
- E: MNIST handwritten digit database
On the example of Classifying Stars, what are the task T, the performance measure P and the experience E?
- T: classification of celestial bodies
- P: accuracy of classifying
- E: classificatios of astronomers
What method is used to classify stars?
learning of multiple decision trees and combining the best rules of each tree
On the example of the Market Basket Analysis, what are the task T, the performance measure P and the experience E?
- T: discover items that are frequently bought together
- P: ? possibly revenue of those items
- E: Supermarket check-out data
What types of different Learning Scenarios are there?
- Supervised Learning
- Semi-supervised Learning
- Reinforcement Learning
- Unsupervised Learning
What is Supervised Learning?
- a lot of labeled examples are provided for training purposes
- machine has to assign labels to examples
- concept learning, classification, regression
What is Semi-supervised Learning?
- a few labeled examples are provided for training purposes
- machine has to assign labels to examples
What is Reinforcement Learning?
- there are no labeled examples for training purposes
- machine only receives feedback on the labelling assignment it does
What is Unsupervised Learning?
- there is no information except the training examples
- clustering, subgroup discovery, association rule discovery
Assign the following examples to the correct types of Learning Scenarios.
- In a video game you find out what to do by how many xp you receive for different actions.
- You download a few webpages and classify them into various types of webpages. then you tell an algorithm to classify every webpage it finds.
- An algorithm receives a pack of thousands of tweets and the instruction to sort them into clusters.
- A handwritten letter is scanned and run through a handwritten character recognition software.
- Reinforcement Learning
- Semi-supervised Learning
- Unsupervised Learning
- Supervised Learning
What is Inductive Learning?
- Given: input x and output f(x) of a function
- Not given: function f
- Problem: given a set of training examples, find a hypothesis h that is as close to the function f as possible, on all examples (so it must generalize from the training examples)
- it ignores prior knowledge
- it assumes that examples are given
What is Ockham’s Razor and how does it pertain to curve fitting in the Inductive Learning Method?
“The simplest explanation is often the best/correct explanation.”
When trying to fit a curve to data points, the best curve for machine learning is the curve that is both simple and mostly right (it doesn’t necessarily have to hit all points but should be relatively easy to foresee into the future.)
What is Overfitting?
A curve is overfitting if its made to fit all points at the expense of being too complex and inconsistent. The curve can’t realistically be used for other data points because it’s too fitted for the example data points.
How can Overfitting be avoided?
Keep a separate validation set (different from training and test sets) to watch the performance. If the error on the validation set rises, stop training.
How does Performance Measurement work? How do we know that we have reached the closest possible solution?
- use theorems of computational and statistical learning theory
- try the solution h on a new set of examples where f is known
How did the “Pigeons as Art Experts” experiment (Watanabe et al 1995, 2001) work and what were its findings?
Pigeons were presented with paintings of Chagall and Van Gogh. They received food when they pecked on paintings by Van Gogh.
After some time the pigeons were able to differentiate between the two artists with 95% accuracy when shown paintings they’ve been trained on and 85% accuracy on previously unseen paintings.