8
votes
Accepted
Neural network for game
Neural networks do not directly take actions in games. Instead, some code needs to supply the current state of the game to the neural network, interpret its output and take the action. Typically yet ...
- 30.2k
4
votes
Why can we have misclassifications for a perfect model in logistic regression?
Since $g$ is your logistic regression model, over data samples $x$, the output of $g(x)$ is a scalar value between $0$ and $1$ that is usually interpreted as a probability value.
We have that $g(x)=\...
- 2,443
4
votes
What is a pipeline in machine learning?
A data pipeline consists of 3 main steps
data collection (e.g. you collect images of cats from different sources)
data transformation (e.g. you make the images all have the same dimensions and maybe ...
- 39.5k
3
votes
is there a mathematical explanation of precision and recall tradeoff?
The tradeoff between precision and recall occurs because increasing the threshold for classification will result in fewer false positives (increasing precision) but also more false negatives (...
- 131
3
votes
What is a pipeline in machine learning?
A "pipeline" typically refers to a chain of methods where the output of the one is used as the input of another method.
This could be, e.g., a "preprocessing pipeline" where ...
- 156
3
votes
Accepted
Regression loss conditioned by the ground-truth values
Your suggestion should work to focus the ML more on larger angle examples.
You may want to try a slightly simpler approach of weighting the loss (or the resulting gradient) by a factor depending on ...
- 30.2k
3
votes
Accepted
Can mini-batches for stochastic gradient be balanced but not representative of the training data?
The problem is, what mathematical definition do you give to "balanced" and "representative"?
Balanced usually means that classes are uniformly distributed, but then you are ...
- 1,333
2
votes
Accepted
NLP "small" model to improve "big" model
When training the model for NLP is it important to get rid of data which has "bad semantic" for learning process?
No, this is backwards for classifiers such as the one you are training.*
...
- 30.2k
2
votes
the best choice to reduce a features vector
Feature selection -- the case in which the features are highly correlated is the prototypical case in which you want to select a subset of independent features that allows for an equal performance. ...
- 31
2
votes
Accepted
Generator loss not decreasing while training GAN
Without looking too much at the code, as this is not a place to ask debugging questions, I'll give some advice on how to potentially solve your problems. I'll assume your code is operational (its ...
- 2,083
2
votes
how to determine the number of units for dense layer for transfer learning?
Not only the units but also the number of layers... you can reason over something like "how complex is your task", but usually we resort to grid search over some educated guesses (like 2/3 ...
- 1,333
2
votes
Is it possible that Precision and Recall increase together?
Often references to the precision-recall trade-off are discussing setting the classification threshold for a probabilistic classifier. A probabilistic classifier is one that returns a probability of ...
- 121
1
vote
Do GANs have constant running time?
The question is a bit ill defined... usually when we want some bound on the running time, we have to say with respect to what
For example:
sorting is O(nlogn) wrt the size of the input
Transformer is ...
- 1,333
1
vote
Is it possible that Precision and Recall increase together?
PR curves need not be monotonic.
Suppose some model, such as a logistic regression, makes predictions p below and that the true outcomes are ...
- 548
1
vote
how to determine the number of units for dense layer for transfer learning?
In adition to @Alberto answer,
Start by the same number of layer and units you removed from original model.
If the problem is the same, this will be probably the best solution.
After that, if the ...
- 111
1
vote
Is it possible to do machine learning on encrypted images?
The short answer is No.
The long answer is maybe, if you use Homomorphic encryption.
Homomorphic encryption is the conversion ...
- 111
1
vote
Accepted
The training process of a conditional GAN
I assume you mean how to label the image and class inputs since the discriminator can reasonably output either "real" or "fake" labels for either of those inputs, and you generally ...
- 30.2k
1
vote
Accepted
What is the potential issue of nested neural networks
Isn't this just a very short recurrent neural network? Same issues apply, although they are less severe since you aren't applying as many recurrent iterations. Once you start "nesting" them ...
- 737
1
vote
Accepted
In the conditional GAN (cGAN) architecture, why does the discriminator need conditional variable?
Because otherwise there is no conditioning... consider the case where you condition the generator but not the discriminator: given an image and a label, the generator proposes an image, which will be ...
- 1,333
1
vote
If the unigram precision is (N-1)/N, then the bigram precision is :
Unigram and bigram accuracy is a measure used in machine translation to assess the quality of a machine-generated translation compared to a reference translation.
Unigram accuracy is the number of ...
Only top scored, non community-wiki answers of a minimum length are eligible