COMPUTER SCIENCE AND ENGINEERING
MACHINE LEARNING
|
Question
[CLICK ON ANY CHOICE TO KNOW THE RIGHT ANSWER]
|
|
|
around a hundred
|
|
|
Several hundred exmaples
|
|
|
A few thousand, ideally tens of thousands.
|
|
|
None of the above
|
Detailed explanation-1: -You can train neural network with one sample, you’d just overfit to it. Moreover, there are some recent results that in some cases neural networks with few orders of magnitude more parameters than samples can achieve better test set performance than smaller networks.
Detailed explanation-2: -But the rule is: You don’t have to start with less than 50 data points. But often 50 observations are enough to develop a feeling for the data structure. That’s a lot of value. Because then you can think about which data you need and what you have to do for it.
Detailed explanation-3: -100 number of images is quite low for a CNN algorithm. Appropriate number of samples depends on the specific problem, and it should be tested for each case individually. But a rough rule of thumb is to train a CNN algorithm with a data set larger than 5, 000 samples for effective generalization of the problem.
Detailed explanation-4: -If you’ve talked with me about starting a machine learning project, you’ve probably heard me quote the rule of thumb that we need at least 1, 000 samples per class.