5 votes

What is the computational complexity of the forward pass of a convolutional neural network?

What is the time complexity? The time complexity of an algorithm is the number of basic operations, such as multiplications and summations, that the algorithm performs. The time complexity is usually ...
nbro's user avatar
  • 40.5k
2 votes

Instead of accumulating the gradient, can we accumulate loss values?

Accumulating the loss like that doesn't improve the memory requirements, because the memory consumption depends on the size of your computational graph. In other words, each time you add a term to the ...
Chillston's user avatar
  • 1,704
1 vote

Unable to understand Figure 3.13 Artificial Intelligence: a Modern Approach

The table's "Nodes" column uses rough approximations, as do most of the values in the table, because it is trying to give an intuition about scaling, and not accurate predictive values for ...
Neil Slater's user avatar
  • 32.1k
1 vote

What is the space complexity for training a neural network using back-propagation?

I will not tell you what the exact space complexity of training an FFNN with GD and BP is (because that actually depends on the specific implementation of GD and BP and I don't want to dive into the ...
nbro's user avatar
  • 40.5k
1 vote
Accepted

What is the space complexity of breadth-first search?

The space complexity of the breadth-first search algorithm is $O(b^d$) in the worst case, and it corresponds to the largest possible number of nodes that may be stored in the frontier at once, where ...
nbro's user avatar
  • 40.5k
1 vote

Why is the space-complexity of greedy best-first search is $\mathcal{O}(b^m)$?

I was struggling with the same question. This is what I came up with after thinking it through. With depth-first-search, you backtrack to a node that is a non-expanded child of your parent (or the ...
Thomas's user avatar
  • 11
1 vote
Accepted

Why is the space-complexity of greedy best-first search is $\mathcal{O}(b^m)$?

After spending some time on the problem, I concluded that it is due to the fact that we need to store the heuristic function evaluations for all nodes during the traversal. So, one might claim that it ...
iRestMyCaseYourHonor's user avatar

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