Community Digest

Top new questions this week:

Can classification model B trained on data labeled by classification model A exceed the performance of model A?

Let's say that I have a small or medium sized dataset of images, say 50,000. I use transfer learning to train a deep learning classification model. Call this model A. Model A is deemed to have good ...

classification predictive-modeling  
asked by AJV Score of 4
answered by Nuclear Hoagie Score of 4

NLP : What is the difference between Authorship Attribution, Authorship Identification and Authorship Recognition?

I have to write my Master's thesis on this topic (I'm in Natural Language Processing) and while I sometimes see these terms used interchangeably other sources seem to emphasize the fact that there are ...

nlp  
asked by Yan Djin Score of 2

Task of regression on graphs

Which tools are available to extract features from a graph. After that, I would like to perform regressions on those features. Initially, I was thinking about using the adjacency matrix of the graph. ...

regression feature-extraction graphs  
asked by Tereso del Río Almajano Score of 2

How can i deal with this overfitting?

I trained my data over 40 epochs but got finally this shape. How can I deal with this problem? Please as I used 30.000 for training and 5000 for testing and ...

deep-learning overfitting learning-rate  
asked by Lei Score of 1
answered by Nicolas Martin Score of 0

How can I use a confusion matrix in image captioning?

I read that a confusion matrix is used with image classification but if I need to draw it with image captioning how to use it or ...

computer-vision confusion-matrix  
asked by Lei Score of 1
answered by Erwan Score of 1

Regularizing the intercept

I am reading The Elements of Statistical Learning and regarding regularized logistic regression it says: "As with the lasso, we typically do not penalize the intercept term" and I am ...

regularization  
asked by ChuckNoise Score of 1
answered by lpounng Score of 0

How do I design a random forest split with a "not sure" category?

Let's say I have data with two target labels, A and B. I want to design a random forest that has three outputs: A, B and Not sure. Items in the Not sure category would be a mix of A and B that would ...

random-forest decision-trees  
asked by cjm2671 Score of 1
answered by Brian Spiering Score of 1

Greatest hits from previous weeks:

How to get accuracy, F1, precision and recall, for a keras model?

I want to compute the precision, recall and F1-score for my binary KerasClassifier model, but don't find any solution. Here's my actual code: ...

machine-learning neural-network deep-learning classification keras  
asked by ZelelB Score of 52
answered by Tasos Score of 53

How to draw Deep learning network architecture diagrams?

I have built my model. Now I want to draw the network architecture diagram for my research paper. Example is shown below:

machine-learning neural-network deep-learning svm software-recommendation  
asked by Muhammad Ali Score of 175
answered by Pablo Rivas Score of 127

What are deconvolutional layers?

I recently read Fully Convolutional Networks for Semantic Segmentation by Jonathan Long, Evan Shelhamer, Trevor Darrell. I don't understand what "deconvolutional layers" do / how they work. The ...

neural-network convnet convolution  
asked by Martin Thoma Score of 269
answered by David Dao Score of 286

What is the "dying ReLU" problem in neural networks?

Referring to the Stanford course notes on Convolutional Neural Networks for Visual Recognition, a paragraph says: "Unfortunately, ReLU units can be fragile during training and can "die". For ...

machine-learning neural-network deep-learning  
asked by tejaskhot Score of 176
answered by Neil Slater Score of 182

Sentence similarity prediction

I'm looking to solve the following problem: I have a set of sentences as my dataset, and I want to be able to type a new sentence, and find the sentence that the new one is the most similar to in the ...

python nlp scikit-learn similarity text  
asked by lte__ Score of 33
answered by Harman Score of 38

How do you visualize neural network architectures?

When writing a paper / making a presentation about a topic which is about neural networks, one usually visualizes the networks architecture. What are good / simple ways to visualize common ...

machine-learning neural-network deep-learning visualization  
asked by Martin Thoma Score of 151
answered by Alex Lenail Score of 74

Calculation and Visualization of Correlation Matrix with Pandas

I have a pandas data frame with several entries, and I want to calculate the correlation between the income of some type of stores. There are a number of stores with income data, classification of ...

python statistics visualization pandas  
asked by gdlm Score of 37
answered by AN6U5 Score of 28

Can you answer these questions?

sklearn - StandardScaler - Use in Production

I transformed my input data using StandardScaler as given here: https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html Code looks like this: ...

scikit-learn  
asked by ceds Score of 1

Is Object Detection Android app code available for ONNX/ORT object detection models?

I have a trained Object detection model in the ONNX format (optimized to run on mobile phones). I have converted that model into the ORT format (which is also a format that is optimized to run on ...

computer-vision object-detection  
asked by skumaravel Score of 1

Get negative predicted value in Support Vector Regresion (SVR)

I am doing Covid-19 cases prediction using SVR, and getting negative values, while there should be no number of Covid-9 cases negative. Feature input that I was used is mobility factor (where have ...

regression svm prediction svr  
asked by Ardy Score of 1
answered by Erwan Score of 0
You're receiving this message because you subscribed to the Data Science community digest.
Unsubscribe from this community digest       Edit email settings       Leave feedback       Privacy
Stack Overflow

Stack Overflow, 110 William Street, 28th floor, New York, NY 10038

<3