4 votes
Accepted

How can I estimate how many photos I need to train ResNet-50 for image classification?

What you want to calculate/estimate is known as the sample complexity in computational learning theory. If you knew the VC dimension of the neural network, you may be able to estimate the sample ...
user avatar
  • 34.4k
3 votes
Accepted

Is there a way to define the boundaries of the optimal size of a training set?

For a finite value to be 'optimal,' typically you need some benefit from more paired up with some cost for more, and eventually the lines cross because the benefit decreases and the cost increases. ...
user avatar
3 votes

How does size of the dataset depend on VC dimension of the hypothesis class?

Given a hypothesis set $H$, the set of all possible mappings from $X\to Y$ where $X$ is our input space and $Y$ are our binary mappings: $\{-1,1\}$, the growth function, $\Pi_H(m)$, is defined as the ...
user avatar
3 votes
Accepted

How does size of the dataset depend on VC dimension of the hypothesis class?

From [1] we know that we have the following bound between the test and train error for i.i.d samples: $$ \mathbb{P}\left(R \leqslant R_{emp} + \sqrt{\frac{d\left(\log{\left(\frac{2m}{d}\right)}+1\...
user avatar
  • 1,663
2 votes

How does size of the dataset depend on VC dimension of the hypothesis class?

The VC dimension represents the capacity (the same Vapnik, the letter V from VC, calls it the "capacity") of a model (or, in general, hypotheses class), so a model with a higher VC dimension has more ...
user avatar
  • 34.4k
1 vote

Is there any practical application of knowing whether a concept class is PAC-learnable?

Is there any practical application of knowing whether a concept class is PAC-learnable? If you know that a concept class is PAC-learnable (i.e. its VC dimension is finite), then there's a possibility ...
user avatar
  • 34.4k
1 vote

Is there a way to define the boundaries of the optimal size of a training set?

In general, the larger the training set, the better. See The Unreasonable effectiveness of Data, though this article is quite dated (written in 2009). Xavier Amatriain, a researcher at Netflix has a ...
user avatar
  • 1,134

Only top scored, non community-wiki answers of a minimum length are eligible