Skip to main content
Data Science

Nice Question

 Nice Question
Question score of 10 or more. This badge can be awarded multiple times.
Awarded 1209 times.
Why do we use a Gaussian kernel as a similarity metric?
Awarded Oct 30 at 17:48
How do you evaluate ML model already deployed in production?
Awarded Oct 24 at 19:08
Is There a Way to Re-Calibrate Predicted Probabilities After Using Class Weights?
Awarded Oct 3 at 17:37
How to determine input shape in keras?
Awarded Sep 21 at 22:05
Is class imbalance really a problem in machine learning?
Awarded Sep 3 at 18:48
Is CUDA 13 a thing (or am I misinterpreting something)?
Awarded Aug 29 at 17:08
Imbalanced data causing mis-classification on multiclass dataset
Awarded Aug 21 at 20:35
What knowledge do I need in order to write a simple AI program to play a game?
Awarded Aug 21 at 17:23
Neural network obfuscation
Awarded Aug 5 at 16:46
Training value neural network AlphaGo style
Awarded Jul 30 at 17:02
Gaussian Mixture Models as a classifier?
Awarded Jul 18 at 10:51
Should I rescale tfidf features?
Awarded Jun 4 at 22:21
Chi-square as evaluation metrics for nonlinear machine learning regression models
Awarded May 22 at 12:06
Does training a neural network on a combined dataset outperform sequential training on individual datasets?
Awarded May 19 at 17:18
Are validation sets necessary for Random Forest Classifier?
Awarded May 18 at 20:31
Python : Feature Matching + Homography to find Multiple Objects
Awarded May 17 at 14:42
How does dropout work during testing in neural network?
Awarded May 11 at 6:07
Optimising for Brier objective function directly gives worse Brier score than optimising with custom objective - what does it tell me?
Awarded Apr 22 at 12:34
What is the difference between residual sum of squares and ordinary least squares?
Awarded Apr 22 at 10:01
Neural network to find errors in training data
Awarded Apr 19 at 7:34
Why is my Keras model not learning image segmentation?
Awarded Apr 14 at 16:23
Why is 10000 used as the denominator in Positional Encodings in the Transformer Model?
Awarded Apr 11 at 9:50
How many parameters in a Conv2d Layer?
Awarded Apr 4 at 15:36
In training a neural network, why don’t we take the derivative with respect to the step size in gradient descent?
Awarded Mar 24 at 12:17
What size language model can you train on a GPU with x GB of memory?
Awarded Mar 10 at 11:26
How are Q, K, and V Vectors Trained in a Transformer Self-Attention?
Awarded Feb 26 at 17:10
Kaggle notebook Vs Google Colab
Awarded Feb 15 at 17:32
Is it valuable to normalize/rescale labels in neural network regression?
Awarded Jan 3 at 0:36
How to estimate the variance of regressors in scikit-learn?
Awarded Jan 1 at 9:33
Why does everyone use BERT in research instead of LLAMA or GPT or PaLM, etc?
Awarded Dec 18, 2024 at 21:40
Adding feature leads to worse results
Awarded Dec 11, 2024 at 10:16
what is the difference between "fully developed decision trees" and "shallow decision trees"?
Awarded Dec 10, 2024 at 5:08
Nested cross-validation and selecting the best regression model - is this the right SKLearn process?
Awarded Dec 5, 2024 at 14:12
What is the correct meaning and interpretation of p-values?
Awarded Nov 19, 2024 at 8:36
How to perform feature selection on dataset with categorical and numerical features?
Awarded Nov 17, 2024 at 14:10
AdaBoost implementation and tuning for high dimensional feature space in R
Awarded Nov 17, 2024 at 14:10
When to use mean vs median
Awarded Nov 11, 2024 at 7:55
Can we remove features that have zero-correlation with the target/label?
Awarded Nov 7, 2024 at 23:35
What are the inputs to the first decoder layer in a Transformer model during the training phase?
Awarded Nov 4, 2024 at 4:32
Should you use random state or random seed in machine learning models?
Awarded Oct 30, 2024 at 17:47
Proper masking in the transformer model
Awarded Sep 23, 2024 at 18:20
ReLU vs Leaky ReLU vs ELU with pros and cons
Awarded Aug 28, 2024 at 13:06
Loss Function for Probability Regression
Awarded Jul 7, 2024 at 2:55
Why Leaky ReLU is not so common in real practice?
Awarded Jun 30, 2024 at 10:56
Cosine similarity vs The Levenshtein distance
Awarded Jun 27, 2024 at 12:57
What is affine transformation in regard to neural networks?
Awarded Jun 3, 2024 at 19:26
Imbalanced dataset in MLP classifier in python
Awarded May 26, 2024 at 11:10
Transform an Autoencoder to a Variational Autoencoder?
Awarded May 22, 2024 at 1:22
dataframe.columns.difference() use
Awarded May 21, 2024 at 7:25
What is the meaning of a quadratic relation when r = 0?
Awarded May 16, 2024 at 1:19
How to prevent vanishing gradient or exploding gradient?
Awarded May 13, 2024 at 0:40
Convolutional network for classification, extremely sensitive to lighting
Awarded May 8, 2024 at 6:55
Why k-fold cross validation (CV) overfits? Or why discrepancy occurs between CV and test set?
Awarded May 5, 2024 at 12:32
Clustering of documents using the topics derived from Latent Dirichlet Allocation
Awarded Apr 13, 2024 at 21:18
What is the difference between BERT and Roberta
Awarded Apr 5, 2024 at 5:47
What is the correct way to call Keras flow_from_directory() method?
Awarded Mar 23, 2024 at 23:07
Why does prompt engineering work, since prompt engineering questions don't appear as training data?
Awarded Mar 16, 2024 at 15:51
Multivariate Time-Series Clustering
Awarded Mar 6, 2024 at 13:47
Decision Trees - how does split for categorical features happen?
Awarded Feb 19, 2024 at 7:46
Cutting numbers into fixed buckets
Awarded Feb 6, 2024 at 16:45
1
2 3 4 5
…
21