Most Popular
1500 questions
8
votes
1 answer
How to predict advantage value in deep reinforcement learning
I'm currently working on a collection of reinforcement algorithms: https://github.com/lhk/rl_gym
For deep q-learning, you need to calculate the q-values that should be predicted by your network. There are many strategies: monte-carlo,…
lhk
- 181
- 3
8
votes
1 answer
GAN vs DCGAN difference
I am trying to understand the key difference between GAN and DCGAN.
I know that DCGAN uses a convolutional network. But:
What data is better to push into GAN and what data fits better to DCGAN?
Does DCGAN work better with small data dimensions?
CezarySzulc
- 257
- 3
- 10
8
votes
2 answers
Synthetic Gradients - what's the practical benefit?
I can see two motives to use Synthetic Gradients in RNN:
To speed up training, by imediately correcting each layer with predicted gradient
To be able to learn longer sequences
I see problems with both of them. Please note, I really like…
Kari
- 2,686
- 1
- 17
- 47
8
votes
1 answer
How can you build a model that reads out receipts and invoices?
The objective is to build a model that is capable of identifying information on receipts and invoices that can look completely different.
I've had a discussion with my brother about the right approach. I have attached an example, here the original…
Spurious
- 181
- 1
- 3
8
votes
3 answers
Why do we use gradients instead of residuals in Gradient Boosting?
I have found mentions of two advantages in using gradients instead of actual residuals:
1) Using gradients will allow us to plug in any loss function (not just mse) without having to change our base learners to make them compatible with the loss…
eyio
- 81
- 1
- 2
8
votes
3 answers
R vs. Python Decision Tree
From my experiences the R Decision tree returns more accurate results than the python decision tree. Can anymore confirm this assumption and maybe knows the reason?
Rene B.
- 369
- 1
- 7
- 13
8
votes
3 answers
Good performance metrics for multiclass classification problem besides accuracy?
I am trying to solve a multiclass classification problem. The dataset is balanced. I have been using accuracy as a performace metric till now. Are there any other good performance metrics for this task?
I already know about precision and recall but…
Kishan Kumar
- 645
- 2
- 7
- 11
8
votes
3 answers
What is normalization for?
I am new in python and data science (and not great in math). I am learning machine learning. I got following normalize function. Can you please explain what does this normalize function do?
def normalize(array):
return (array - array.mean()) /…
Pranit Kothari
- 207
- 2
- 5
8
votes
1 answer
Bag of Visual Words
What I am trying to do:
I am trying to classify some images using local and global features.
What I have done so far:
I have extracted sift descriptors for each image and I am using this as my input for k-means to create my vocabulary from all of…
Kevin
- 261
- 3
- 7
8
votes
2 answers
Ratio between embedded vector dimensions and vocabulary size
Using Embedding layer in Keras on a fairly small vocabulary (~300), I am looking at how to choose the output of this layer (dense vector) when given a 300 dimension vector. I think that the embedded vector need to have a minimum length to be able…
0xmax
- 373
- 1
- 2
- 10
8
votes
2 answers
Pros/Cons of stop word removal?
What are the pros / cons of removing stop words from text in the context of a text classification problem, I'm wondering what the best approach is (i.e. to remove or not to remove)?
I've read somewhere (but can't locate the reference) that it may be…
Jimmy Collins
- 253
- 2
- 4
8
votes
1 answer
K-means clustering of word embedding gives strange results
I'm trying to cluster words based on pre trained embeddings. I ran a simple experiment where I obtained around 100 words relating to "food taste", obtained word embeddings from a pre-trained set, and tried to run k-means on the result.
I do get…
Thusitha
- 111
- 1
- 5
8
votes
2 answers
How to delete entire row if values in a column are NaN
I'd like to drop all the rows containing a NaN values pertaining to a column. Lets assume I have a dataset like this:
Age Height Weight Gender
12 5'7 NaN M
NaN 5'8 160 M
32 5'5 165 NaN
21 NaN 155 F
55 …
uharsha33
- 331
- 3
- 4
- 8
8
votes
1 answer
Question on bias-variance tradeoff and means of optimization
So I was wondering how does one, for example, can best optimize the model they are trying to build when confronted with issues presented by high bias or high variance. Now, of course, you can play with the regularization parameter to get to a…
Zer0k
- 155
- 5
8
votes
1 answer
How to apply the gradient of softmax in backprop
I recently did a homework where I had to learn a model for the MNIST 10-digit classification. The HW had some scaffolding code and I was supposed to work in the context of this code.
My homework works / passes tests but now I'm trying to do it all…
SaldaVonSchwartz
- 299
- 1
- 3
- 7