All Questions
25,238
questions
0
votes
0answers
3 views
Why does bidirectional LSTM have half the parameter count compared to LSTM in keras?
I want to implement a unidirectional and a bidirectional LSTM in tensorflow keras wrapper with the same amount of units. As an example I implement the unidirectional LSTM with 256 units, and the ...
0
votes
0answers
5 views
Python Machine learning - Predictions based on several inputs
I have in total three columns of data in a dataframe, lets say coulmn_a, coulmn_b and column_res with 40 datapoints in each column.
Is it possible to train a LSTM model based on column_a and column_b ...
-1
votes
1answer
15 views
Which other algorithms fit residuals like XGBoost?
XGBoost and standard gradient boosting train learners to fit the residuals rather than the observations themselves. I understand that this aspect of the algorithm matches the boosting mechanism which ...
0
votes
1answer
12 views
Using word embeddings with additional features
I have the set of queries for classification task using Gradient Boosting Classifier of scikit learn. I want to enrich the model by feeding additional features along with GloVe. How should I approach ...
0
votes
1answer
13 views
DBSCAN Clustering
I used K-means to get the number of clusters for my data(Elbow Method). Then I was trying to see if for some specific hyperparameters can we get the same number of clusters for DBSCAN. I tried Brute-...
2
votes
1answer
29 views
Pattern recognition for strings
So I currently have a text pattern detection challenge to solve at work. I am trying to make an outlier detection algorithm for a database, for string columns.
For example let's say I have the ...
1
vote
1answer
15 views
Why Adaboost SAMME needs f to be estimable?
I am trying to understand the mathematics behind SAMME AdaBoost:
https://web.stanford.edu/~hastie/Papers/samme.pdf
At some stage, the paper adds a constraint for f to be estimable:
I do not ...
0
votes
1answer
20 views
0
votes
0answers
8 views
Model deployment with Flask, Tensorflow Serving and Docker
I am puzzled over this example: https://towardsdatascience.com/deploying-deep-learning-models-using-tensorflow-serving-with-docker-and-flask-3b9a76ffbbda
In the write-up, only the TF Serving is within ...
0
votes
1answer
20 views
Understanding Transfer Learning of Word Embeddings
I can't quite visualize how transfer learning of pre-trained word embeddings is useful in an NLP task( say named entity recognition ) . I'm studying Andrew NG's Sequence Models course and he seems to ...
1
vote
1answer
21 views
Which model is better, one just before overfitting with higher accuracy or one with no overfitting and lower accuracy?
I am training a CNN model.
In the first one I got a training accuracy of 87%(0.29 loss) and validation accuracy of 87%(0.30 loss) at 5th epoch, I kept training it for total of 15 epochs and as ...
0
votes
0answers
9 views
Loss function for group aggregated prediction results
I have a set of individual level data x11, x12, x13... that is grouped into each own groups g1, g2, g3. I'm trying to create a prediction model which predicts y1, y2, y3...
The simplest method would ...
-1
votes
0answers
29 views
How to enter an MSc Data Science program with BSc IT? [closed]
Has anyone managed to enter a masters program in data science with a bachelors in IT? Given that sometimes BSc IT degrees might not be very Maths intensive would completing a PGcert in Mathematics be ...
1
vote
0answers
21 views
How backpropagation works in case of 2 hidden layers?
Imagine the next structure (for simplicity, there's no bias, and activation formatting with sigmoid or relu, just weights). The input has two neurons, the two hidden layers have 3 neurons each, the ...
0
votes
0answers
11 views
Loading very big data csv in excel file crash with Orange [closed]
i loaded big data (more than 500k rows, having 7 features) in csv Excel for classification using ML.
the orange can not load and stop responding. (laptop ram 8GB).
Any tips on how to handle this issue?...

