User Shirish Kulhari

1

4

votes

1

answer

378

views

Probability of a 500 year flood occuring in the next 100 years - comparison of approaches

Oct 13 at 9:57 gunes 17.7k

3

votes

1

answer

34

views

Probability of location based on cell tower signal strength

probability bayesian

Oct 7 at 9:48 BruceET 17.5k

2

votes

1

answer

24

views

Clustering categorical variable values based on continuous target values

machine-learning clustering

Nov 18 at 21:14 user20160 20.9k

2

votes

0

answers

15

views

Research on explaining generalizability of deep learning methods

neural-networks references

Nov 15 at 9:22 Shirish Kulhari 353

2

votes

1

answer

45

views

Program analysis of a coin toss simulator

probability probabilistic-programming

Oct 7 at 20:29 Ron Jensen 213

2

votes

0

answers

22

views

Clustering of very high dimensional data and large number of examples without losing info in dimensions

machine-learning clustering dimensionality-reduction

Sep 15 at 10:10 Shirish Kulhari 353

2

votes

1

answer

44

views

Confusion on how skip gram implementation is formulated

neural-networks word2vec

Sep 2 at 6:21 Alejandro Celis 156

1

vote

0

answers

27

views

+50

Comparison of dispersion measures of different samples with different subsamples

standard-deviation sample-size coefficient-of-variation

Dec 8 at 10:08 Shirish Kulhari 353

1

vote

0

answers

18

views

Finding variation in mean of some parameter for different groups

anova unbalanced-classes

Nov 14 at 21:37 whuber♦ 224k

1

vote

1

answer

28

views

Gaps in histogram for geometric distribution

probability histogram geometric-distribution

Oct 9 at 17:24 quester 306

1

vote

0

answers

16

views

How does Continuous Bag of Words ensure that similar words are encoded as similar embeddings?

natural-language word-embeddings word2vec

Aug 16 at 13:46 Shirish Kulhari 353

1

vote

0

answers

15

views

Understanding how continuous bag of words method learns embedded representations

natural-language word-embeddings word2vec

Aug 13 at 15:49 Shirish Kulhari 353

1

vote

0

answers

43

views

How does Batch Normalization in Machine Learning address covariate shift and speed up training?

neural-networks batch-normalization

Jul 23 at 18:49 Shirish Kulhari 353

1

vote

0

answers

29

views

k-Nearest Neighbors multiclass - what if we can't form the majority?

machine-learning classification k-nearest-neighbour

Mar 24 at 16:22 Shirish Kulhari 353

1

vote

1

answer

187

views

Specifics on weight update calculation in stochastic gradient descent

machine-learning gradient-descent

Jan 26 at 7:30 gunes 17.7k

1

vote

1

answer

888

views

Derivation of Perceptron weight update formula

machine-learning gradient-descent perceptron

Jan 17 '19 at 11:21 Mark.F 398

1

vote

1

answer

43

views

Estimating the distribution over number of clusters in clustering

machine-learning clustering estimation density-estimation

Dec 19 '17 at 19:15 Anony-Mousse 34.7k

1

vote

0

answers

52

views

How are various rules for determining frequency distribution binwidth derived?

histogram frequency binning density-estimation

May 30 '17 at 11:04 Shirish Kulhari 353

0

votes

1

answer

55

views

Effect of rescaling of inputs on loss for a simple neural network

neural-networks normalization

Nov 25 at 14:44 Sycorax says Reinstate Monica 51.4k

0

votes

0

answers

6

views

Find out which attribute of a movie causes the most variation in score

feature-selection

Oct 4 at 20:25 Shirish Kulhari 353

0

votes

1

answer

46

views

Updating posterior probability as more data is given

probability bayesian

Oct 1 at 14:37 DavidF 173

0

votes

0

answers

10

views

Doubt on formulating cost function for GloVe

natural-language word-embeddings

Sep 17 at 16:00 Shirish Kulhari 353

0

votes

1

answer

25

views

Relation between size of parameters and complexity of model with overfitting

machine-learning overfitting

Aug 2 at 14:52 Carsten 136

0

votes

0

answers

17

views

Computing derivatives for backpropagation across a convolution step

neural-networks backpropagation convolution

Jul 29 at 14:43 Shirish Kulhari 353

0

votes

1

answer

20

views

Making sense of indices in 2D convolution operations in convolutional neural networks

neural-networks conv-neural-network convolution

Jul 5 at 8:56 Shirish Kulhari 353

0

votes

0

answers

38

views

Intuitive reasoning behind inverted dropout in neural networks

machine-learning neural-networks dropout

Jun 20 at 11:47 Shirish Kulhari 353

0

votes

0

answers

28

views

Statistically evaluating classification accuracy of machine learning model

machine-learning distributions classification sampling model-evaluation

May 24 at 16:00 Shirish Kulhari 353

0

votes

0

answers

10

views

Determining an appropriate cost function given the type of problem and a hypothesis function

machine-learning supervised-learning

Apr 17 at 13:30 Shirish Kulhari 353

Stack Exchange Network

current community

your communities

more stack exchange communities

Next privilege

Next badge

28 Questions

Probability of a 500 year flood occuring in the next 100 years - comparison of approaches

Probability of location based on cell tower signal strength

Clustering categorical variable values based on continuous target values

Research on explaining generalizability of deep learning methods

Program analysis of a coin toss simulator

Clustering of very high dimensional data and large number of examples without losing info in dimensions

Confusion on how skip gram implementation is formulated

Comparison of dispersion measures of different samples with different subsamples

Finding variation in mean of some parameter for different groups

Gaps in histogram for geometric distribution

How does Continuous Bag of Words ensure that similar words are encoded as similar embeddings?

Understanding how continuous bag of words method learns embedded representations

How does Batch Normalization in Machine Learning address covariate shift and speed up training?

k-Nearest Neighbors multiclass - what if we can't form the majority?

Specifics on weight update calculation in stochastic gradient descent

Derivation of Perceptron weight update formula

Estimating the distribution over number of clusters in clustering

How are various rules for determining frequency distribution binwidth derived?

Effect of rescaling of inputs on loss for a simple neural network

Find out which attribute of a movie causes the most variation in score

Updating posterior probability as more data is given

Doubt on formulating cost function for GloVe

Relation between size of parameters and complexity of model with overfitting

Computing derivatives for backpropagation across a convolution step

Making sense of indices in 2D convolution operations in convolutional neural networks

Intuitive reasoning behind inverted dropout in neural networks

Statistically evaluating classification accuracy of machine learning model

Determining an appropriate cost function given the type of problem and a hypothesis function