Open anthonyche opened 2 years ago
computational effort? Training sample size?
Training sets of size m may not be enough to pick out f The training set is large enough but is bad
𝜹: The probability of failure due to a bad sample 𝜺:
In Bias-Variance analysis looked at components of the generalization error for arbitrary concept classes
Now we will ask about the "learnability" of specific concept classes.
How easy is it to find the target concept in terms of:
Two sources of failure
We introduce two parameters
𝜹: The probability of failure due to a bad sample 𝜺:
The PAC model