Data Science Stack Exchange
Data Science Stack Exchange

Most Popular

more tags
1500 questions
12
votes
2 answers

How does backpropagation works through Max Pooling layer when doing a batch?

Let's assume that we are using a batch size of 100 samples for learning. So in every batch, the weight of every neuron (and bias, etc) is being updated by adding the minus of the learning rate * the average error value that we found using the 100…
Nathan B
  • 241
  • 1
  • 2
  • 5
12
votes
3 answers

How are weights represented in a convolution neural network?

I have been trying to develop a convolution neural network following some guides online. However, most guides I have encountered gloss over an important detail, which is how to programmatically represent the weights in a CNN. As far as I understand,…
D3181
  • 243
  • 1
  • 2
  • 6
12
votes
1 answer

Feature importance with high-cardinality categorical features for regression (numerical depdendent variable)

I was trying to use feature importances from Random Forests to perform some empirical feature selection for a regression problem where all the features are categorical and a lot of them have many levels (on the order of 100-1000). Given that one-hot…
user90772
  • 331
  • 4
  • 11
12
votes
1 answer

XGBoost for binary classification: choosing the right threshold

I am working on a highly-imbalanced binary-labeled dataset, where number of true labels is just 7% from the whole dataset. But some combination of features could yield higher than average number of ones in a subset. E.g. we have the following…
Denis Kulagin
  • 281
  • 1
  • 2
  • 8
12
votes
2 answers

Does it make sense to train a CNN as an autoencoder?

I work with analyzing EEG data, which will eventually need to be classified. However, obtaining labels for the recordings is somewhat expensive, which has led me to consider unsupervised approaches, to better utilize our quite large amounts of…
Kaare
  • 267
  • 1
  • 2
  • 8
12
votes
3 answers

How to animate growth of a social network?

I am seeking for a library/tool to visualize how social network changes when new nodes/edges are added to it. One of the existing solutions is SoNIA: Social Network Image Animator. It let's you make movies like this one. SoNIA's documentation says…
Wojciech Walczak
  • 916
  • 12
  • 23
12
votes
1 answer

Gradient Boosting Tree: "the more variable the better"?

From the tutorial of the XGBoost, I think when each tree grows, all the variables are scanned to be selected to split nodes, and the one with the maximum gain split will be chosen. So my question is that what if I add some noise variables into the…
WCMC
  • 465
  • 1
  • 5
  • 11
12
votes
2 answers

Clustering high dimensional data

TL;DR: Given a big image dataset (around 36 GiB of raw pixels) of unlabeled data, how can I cluster the images (based on the pixel values) without knowing the number of clusters K to begin with? I am currently working on an unsupervised learning…
sunside
  • 223
  • 1
  • 2
  • 8
12
votes
5 answers

Machine Learning vs Deep Learning

I am a bit confused by the difference between the terms "Machine Learning" and "Deep Learning". I have Googled it and read many articles, but it is still not very clear to me. A known definition of Machine Learning by Tom Mitchell is: A computer…
user2835098
  • 133
  • 1
  • 6
12
votes
2 answers

What is a tower?

In many tensorflow tutorials (example) "towers" are mentioned without a definition. What is meant by that?
Benedikt S. Vogler
  • 245
  • 2
  • 11
12
votes
3 answers

Would you recommend feature normalization when using boosting trees?

For some machine learning methods it is recommended to use feature normalization to use features that are on the same scale, especially for distance based methods like k-means or when using regularization. However, in my experience, boosting tree…
Soerendip
  • 724
  • 1
  • 9
  • 16
12
votes
2 answers

How exactly does DropOut work with convolutional layers?

Dropout (paper, explanation) sets the output of some neurons to zero. So for a MLP, you could have the following architecture for the Iris flower dataset: 4 : 50 (tanh) : dropout (0.5) : 20 (tanh) : 3 (softmax) It would work like…
Martin Thoma
  • 18,880
  • 35
  • 95
  • 169
12
votes
6 answers

Check similarity between time series

I have time series of parameters A, B, C and D. All of them are under influence of the same major conditions, but each one has minor differences. They are placed in different locations, A, B, C are in local1 and D is in local2. I would like to know…
KcFnMi
  • 343
  • 1
  • 4
  • 8
12
votes
1 answer

Train on batches in Tensorflow

I'm currently trying to train a model on a large csv file (>70GB with more than 60 million rows). To do so I'm using tf.contrib.learn.read_batch_examples. I'm struggling in understanding how this function actually reads the data. If I'm using a…
Nico
  • 121
  • 1
  • 3
12
votes
1 answer

Spark ALS: recommending for new users

The question How do I predict the rating for a new user in an ALS model trained in Spark? (New = not seen during training time) The problem I'm following the official Spark ALS tutorial…
ciri
  • 236
  • 2
  • 7
1 2 3
…
99 100