Skip to main content
Arya McCarthy's user avatar
Arya McCarthy's user avatar
Arya McCarthy's user avatar
Arya McCarthy
  • Member for 7 years, 3 months
  • Last seen this week
60 votes

Is Wikipedia's page on the sigmoid function incorrect?

45 votes

Statistics of lottery

36 votes
Accepted

What is the role of temperature in Softmax?

36 votes

Is there a name for the opposite of the gambler's fallacy?

31 votes

Is a neural network essential for deep learning?

12 votes
Accepted

What is a random variable in ADAM optimizer?

11 votes
Accepted

Why do we multiply log likelihood times -2 when conducting MLE?

10 votes
Accepted

Are text generation models generative or discriminative?

10 votes
Accepted

Probability question - Bernoulli trials vs Binomial distribution

9 votes
Accepted

What is the difference between the Viterbi algorithm and beam search?

8 votes
Accepted

Attention Mechanisms in Tranformers, effect of using more parameters than Keys and Queries

8 votes
Accepted

Number of features in multiclass Logistic Regression with categorical predictor

8 votes
Accepted

Normalizing flow training

7 votes
Accepted

complex models have low bias and high variance

7 votes
Accepted

Why is using the mean and variance of entire training set impractical in batch normalization

7 votes
Accepted

Logistic Regression on multiple classes (Shouldn't it be only on binary?)

7 votes

How to visualize Dirichlet distribution (with more than 3 targets)?

7 votes
Accepted

Base of the logarithm used for Shannon Entropy when considering a vocabulary

7 votes
Accepted

Order agnostic autoregressive sequence probability

7 votes
Accepted

Converse of pairwise Markov property

6 votes

"Information" Correlation

6 votes
Accepted

Why do large LMs use the transpose of the word embeddings matrix in the classification head?

6 votes
Accepted

Do we use maximum likelihood or cross entropy Loss for training skip-gram model?

6 votes
Accepted

What is the role of model likelihood?

6 votes

Why is a 100 heads run surprising?

5 votes
Accepted

Why were/are LSTMs popular for so long for NLP?

5 votes

Word2vec that can distinguish words with different meanings

5 votes
Accepted

Why does ridge regression only have one hyperparameter $\lambda$?

5 votes
Accepted

How do Bayesians deal with the fact that the treatment of fixed parameters as random variables can lead to inappropriate subjective probabilities?

5 votes
Accepted

BERT MLM - 80% [MASK], 10% random words and 10% same word - how does this work?

1
2 3 4 5 6