Skip to main content
Data Science

Favorite Question

 Favorite Question
Question saved by 25 users. This badge can be awarded multiple times.
Awarded 103 times.
Does gradient descent always converge to an optimum?
Awarded Jul 12 at 16:52
Is it always better to use the whole dataset to train the final model?
Awarded Mar 25 at 17:02
Why are Machine Learning models called black boxes?
Awarded Mar 14 at 16:12
When to use Random Forest over SVM and vice versa?
Awarded Feb 27 at 6:26
What does from_logits=True do in SparseCategoricalcrossEntropy loss function?
Awarded Jan 17 at 17:26
Neural Network for Multiple Output Regression
Awarded Jan 8 at 20:43
Why is ReLU used as an activation function?
Awarded Sep 12, 2023 at 19:10
What is the relationship between the accuracy and the loss in deep learning?
Awarded Aug 30, 2023 at 14:55
Is it necessary to standardize your data before clustering?
Awarded Jul 24, 2023 at 13:36
ValueError: Input contains NaN, infinity or a value too large for dtype('float32')
Awarded Apr 24, 2023 at 17:36
Cosine similarity versus dot product as distance metrics
Awarded Apr 20, 2023 at 11:36
Latent Dirichlet Allocation vs Hierarchical Dirichlet Process
Awarded Jan 8, 2023 at 4:34
Time Series prediction using LSTMs: Importance of making time series stationary
Awarded Oct 18, 2022 at 9:56
What is the difference between model hyperparameters and model parameters?
Awarded Apr 1, 2022 at 17:57
How to set the number of neurons and layers in neural networks
Awarded Mar 22, 2022 at 14:49
How Do I Learn Neural Networks?
Awarded Jan 25, 2022 at 16:31
What is the difference between bootstrapping and cross-validation?
Awarded Nov 19, 2021 at 22:12
Deep Learning vs gradient boosting: When to use what?
Awarded Oct 29, 2021 at 11:03
Sparse_categorical_crossentropy vs categorical_crossentropy (keras, accuracy)
Awarded Oct 17, 2021 at 21:27
Does XGBoost handle multicollinearity by itself?
Awarded Oct 15, 2021 at 18:46
IDE alternatives for R programming (RStudio, IntelliJ IDEA, Eclipse, Visual Studio)
Awarded Jul 14, 2021 at 3:04
When would one use Manhattan distance as opposed to Euclidean distance?
Awarded Jul 11, 2021 at 12:34
Does scikit-learn have a forward selection/stepwise regression algorithm?
Awarded Mar 29, 2021 at 0:15
What is the positional encoding in the transformer model?
Awarded Mar 25, 2021 at 16:21
What is the difference between Gradient Descent and Stochastic Gradient Descent?
Awarded Mar 12, 2021 at 9:57
What are the use cases for Apache Spark vs Hadoop
Awarded Jan 27, 2021 at 12:33
GBM vs XGBOOST? Key differences?
Awarded Jan 24, 2021 at 18:13
What is "experience replay" and what are its benefits?
Awarded Dec 9, 2020 at 14:03
What is the Q function and what is the V function in reinforcement learning?
Awarded Aug 14, 2020 at 5:19
How do subsequent convolution layers work?
Awarded Aug 12, 2020 at 20:33
How to set batch_size, steps_per epoch, and validation steps?
Awarded Jul 6, 2020 at 12:20
Intuitive explanation of Noise Contrastive Estimation (NCE) loss?
Awarded Jun 18, 2020 at 21:16
Does batch_size in Keras have any effects in results' quality?
Awarded Jun 6, 2020 at 16:25
What is the difference between "equivariant to translation" and "invariant to translation"
Awarded May 28, 2020 at 8:22
How to clone Python working environment on another machine?
Awarded May 19, 2020 at 2:18
What algorithms should I use to perform job classification based on resume data?
Awarded Apr 6, 2020 at 23:30
What is Ground Truth
Awarded Mar 6, 2020 at 9:00
Difference between isna() and isnull() in pandas
Awarded Feb 23, 2020 at 11:55
Number of parameters in an LSTM model
Awarded Feb 12, 2020 at 8:05
Are there free cloud services to train machine learning models?
Awarded Feb 8, 2020 at 8:10
Why should the data be shuffled for machine learning tasks
Awarded Feb 5, 2020 at 5:45
Train/Test/Validation Set Splitting in Sklearn
Awarded Jan 22, 2020 at 10:05
Opening a 20GB file for analysis with pandas
Awarded Jan 19, 2020 at 15:20
Why do we need XGBoost and Random Forest?
Awarded Jan 10, 2020 at 11:10
How to deal with time series which change in seasonality or other patterns?
Awarded Dec 6, 2019 at 11:40
How big is big data?
Awarded Nov 7, 2019 at 0:10
Why do people prefer Pandas to SQL?
Awarded Nov 4, 2019 at 20:25
In supervised learning, why is it bad to have correlated features?
Awarded Sep 20, 2019 at 15:00
Backprop Through Max-Pooling Layers?
Awarded Sep 4, 2019 at 21:15
In softmax classifier, why use exp function to do normalization?
Awarded Sep 4, 2019 at 19:00
Multi GPU in Keras
Awarded Aug 23, 2019 at 17:45
How to calculate mAP for detection task for the PASCAL VOC Challenge?
Awarded Aug 6, 2019 at 10:25
Should a model be re-trained if new observations are available?
Awarded Jul 25, 2019 at 20:20
General approach to extract key text from sentence (nlp)
Awarded May 15, 2019 at 9:05
Cross-entropy loss explanation
Awarded May 13, 2019 at 18:40
The difference between `Dense` and `TimeDistributedDense` of `Keras`
Awarded May 8, 2019 at 10:30
What are some standard ways of computing the distance between documents?
Awarded Apr 29, 2019 at 13:25
Training an RNN with examples of different lengths in Keras
Awarded Apr 29, 2019 at 10:25
What is dimensionality reduction? What is the difference between feature selection and extraction?
Awarded Apr 18, 2019 at 12:45
Clustering geo location coordinates (lat,long pairs)
Awarded Mar 15, 2019 at 21:00
1
2