Necromancer - Badge - Data Science Stack Exchange

Necromancer

Answer a question more than 60 days later with score of 5 or more. This badge can be awarded multiple times.

Awarded 678 times.

what is the interest of TimeDistributed after an LSTM layer?

Awarded yesterday

Leevo

6,0753 gold badges15 silver badges51 bronze badges

Why Is Overfitting Bad in Machine Learning?

Awarded Nov 21 at 20:48

Ram

3334 silver badges6 bronze badges

When to use bayesian linear regression instead of linear regression?

Awarded Nov 20 at 18:41

Brian Spiering

20.5k2 gold badges26 silver badges105 bronze badges

Gumbel-Softmax trick vs Softmax with temperature

Awarded Nov 16 at 23:47

ZNZNZ

1511 silver badge3 bronze badges

Learning rate in logistic regression with sklearn

Awarded Nov 11 at 2:57

David Masip

6,0312 gold badges24 silver badges61 bronze badges

When should one use L1, L2 regularization instead of dropout layer, given that both serve same purpose of reducing overfitting?

Awarded Nov 6 at 22:56

ACB_prgm

511 silver badge2 bronze badges

How does keras calculate accuracy for multi label classification?

Awarded Nov 5 at 8:05

Gianmario Spacagna

1661 silver badge2 bronze badges

Can I use the Softmax function with a binary classification in deep learning?

Awarded Oct 25 at 5:07

Berkay Berabi

1551 silver badge3 bronze badges

In a Transformer model, why does one sum positional encoding to the embedding rather than concatenate it?

Awarded Oct 10 at 10:18

Denziloe

1591 silver badge4 bronze badges

How to adjust the hyperparameters of MLP classifier to get more perfect performance

Awarded Oct 1 at 16:55

Lucas Morin

2,5675 gold badges20 silver badges40 bronze badges

What is the advantage of keeping batch size a power of 2?

Awarded Sep 19 at 13:06

gessulat

1511 silver badge1 bronze badge

Polynomial Kernel Parameters in SVMs

Awarded Sep 13 at 0:17

mprat

2412 silver badges10 bronze badges

Determining size of FC layer after Conv layer in PyTorch

Awarded Aug 22 at 18:25

komunistbakkal

1012 silver badges3 bronze badges

Remove all columns where the entire column is null

Awarded Aug 19 at 21:56

A F

511 silver badge3 bronze badges

Keras difference beetween val_loss and loss during training

Awarded Aug 16 at 19:05

Kermit

5195 silver badges17 bronze badges

What is the difference between FC and MLP in as used in PointNet?

Awarded Aug 7 at 14:25

Dmitry Demidov

1011 silver badge5 bronze badges

How to know the model has started overfitting?

Awarded Jul 25 at 8:11

Juan Antonio Gomez Moriano

1,1971 gold badge8 silver badges17 bronze badges

Keras EarlyStopping callback: Why would I ever set restore_best_weights=False?

Awarded Jul 14 at 20:25

noe

23.8k1 gold badge45 silver badges73 bronze badges

Understanding `get_combination_wise_output_matrix` when investigating a multi-label classification problem

Awarded Jun 29 at 15:16

Alexander Ruch

661 silver badge2 bronze badges

How to train an existing word2vec gensim model on new words?

Awarded Jun 22 at 6:51

Thirupathi Thangavel

2172 silver badges9 bronze badges

How to find the size of a tensor in bytes?

Awarded Jun 14 at 10:03

Hoagy Cunningham

811 silver badge3 bronze badges

What are the good parameter ranges for BERT hyperparameters while finetuning it on a very small dataset?

Awarded May 27 at 3:15

mon

5752 gold badges9 silver badges19 bronze badges

What to set in steps_per_epoch in Keras' fit_generator?

Awarded May 25 at 0:46

noobie2023

1511 silver badge1 bronze badge

Preprocessing for Text Classification in Transformer Models (BERT variants)

Awarded May 9 at 7:32

Fatemeh Rahimi

5493 silver badges16 bronze badges

Why neural networks models do not allow for multiplication of inputs?

Awarded May 8 at 4:50

Elias Hasle

1711 silver badge3 bronze badges

Partitioning Weighted Undirected Graph

Awarded May 5 at 6:20

Kasra Manshaei

6,5321 gold badge20 silver badges45 bronze badges

What does Logits in machine learning mean?

Awarded May 4 at 18:55

noe

23.8k1 gold badge45 silver badges73 bronze badges

What does the descision boundary of a relu look like?

Awarded Apr 26 at 12:26

Ben Reiniger♦

11.2k3 gold badges16 silver badges54 bronze badges

R vs. Python Decision Tree

Awarded Apr 25 at 10:11

nigelhenry

2562 silver badges3 bronze badges

Why do we use gradients instead of residuals in Gradient Boosting?

Awarded Apr 21 at 1:40

David Waterworth

4103 silver badges10 bronze badges

What is the advantage of keeping batch size a power of 2?

Awarded Apr 18 at 20:57

ezekiel

1801 silver badge3 bronze badges

How to determine feature importance in a neural network?

Awarded Apr 12 at 20:03

rodrigo-silveira

1701 silver badge7 bronze badges

issue with oneHotEncoding

Awarded Apr 11 at 19:05

vikas sharma

511 silver badge1 bronze badge

What is the relationship between the accuracy and the loss in deep learning?

Awarded Apr 10 at 9:48

aest

711 silver badge3 bronze badges

t-SNE: Why equal data values are visually not close?

Awarded Mar 31 at 22:56

PSub

7125 silver badges11 bronze badges

Using class weights with validation data in Keras

Awarded Mar 26 at 12:36

Andrei Cana

611 silver badge2 bronze badges

XGBoost custom objective for regression in R

Awarded Mar 21 at 15:33

Kipédène Coulibaly

761 silver badge2 bronze badges

What tokenizer does OpenAI's GPT3 API use?

Awarded Mar 7 at 11:02

pjama

2563 silver badges4 bronze badges

Does gradient descent always converge to an optimum?

Awarded Feb 28 at 12:18

Tuyen

1311 silver badge4 bronze badges

What does Negative Log Likelihood mean?

Awarded Feb 27 at 8:40

oezguensi

5724 silver badges9 bronze badges

ValueError: shapes (1,10) and (2,) not aligned: 10 (dim 1) != 2 (dim 0)

Awarded Feb 24 at 14:06

tmck

511 silver badge2 bronze badges

SHAP value analysis gives different feature importance on train and test set

Awarded Feb 21 at 8:19

Carlos Mougan

6,0822 gold badges16 silver badges47 bronze badges

Conda Verification Failed

Awarded Feb 17 at 18:35

Roel Van de Paar

2052 silver badges12 bronze badges

How to make LightGBM to suppress output?

Awarded Feb 16 at 3:01

banderlog013

1811 silver badge3 bronze badges

In softmax classifier, why use exp function to do normalization?

Awarded Feb 11 at 4:15

komunistbakkal

1012 silver badges3 bronze badges

Difference between IOB and IOB2 format?

Awarded Feb 9 at 16:07

James Mayfield

511 silver badge2 bronze badges

Keras' 'normal' LSTM uses the GPU?

Awarded Feb 9 at 0:02

Michaela

1511 silver badge2 bronze badges

human level performance on ImageNet, top-1 or top-5?

Awarded Feb 8 at 21:56

Salva Carrión

1511 silver badge2 bronze badges

Pandas: how can I create multi-level columns

Awarded Feb 8 at 7:25

Leopold

1711 silver badge2 bronze badges

How can Time Series Analysis be done with Categorical Variables

Awarded Feb 6 at 8:10

Ricardo

1611 silver badge3 bronze badges

Joining tables from different locations in Bigquery

Awarded Feb 1 at 10:38

Soumendra Mishra

2622 silver badges12 bronze badges

Why is orthogonal weights initialization so important for PPO?

Awarded Jan 31 at 16:56

SolomidHero

661 silver badge2 bronze badges

Is feature engineering still useful when using XGBoost?

Awarded Jan 27 at 3:40

Lucas Morin

2,5675 gold badges20 silver badges40 bronze badges

What is the Time Complexity of Linear Regression?

Awarded Jan 19 at 9:11

Carlos Llosa

1511 silver badge2 bronze badges

How to use LeakyRelu as activation function in sequence DNN in keras?When it perfoms better than Relu?

Awarded Jan 4 at 9:25

Somoy Subandhu

511 silver badge2 bronze badges

Train/Test/Validation Set Splitting in Sklearn

Awarded Jan 3 at 7:41

Jorge Barrios

1811 silver badge5 bronze badges

Class token in ViT and BERT

Awarded Jan 2 at 13:51

Mohsen

1111 silver badge3 bronze badges

Does BERT has any advantage over GPT3?

Awarded Dec 20, 2022 at 4:10

Langley

1611 silver badge3 bronze badges

Could Deep Learning be used to crack encryption?

Awarded Dec 10, 2022 at 20:18

manoj

1511 silver badge1 bronze badge

How to disable GPU with TensorFlow?

Awarded Dec 7, 2022 at 12:35

momo

1631 silver badge5 bronze badges

2 3 4 5

…

12 Next