SHASHANK GUPTA's user avatar
SHASHANK GUPTA's user avatar
SHASHANK GUPTA's user avatar
SHASHANK GUPTA
  • Member for 8 years, 4 months
  • Last seen more than a week ago
  • IIIT Hyderabad
289 votes
8 answers
371k views

Micro Average vs Macro average Performance in a Multiclass classification setting

7 votes
1 answer
5k views

Can we compare a word2vec vector with a doc2vec vector?

6 votes
1 answer
4k views

Image Captioning in Keras

5 votes
1 answer
3k views

Optimizing co-occurrence matrix computation

4 votes
1 answer
620 views

Multi-task learning for Multi-label classification?

3 votes
2 answers
5k views

Gensim word2vec training error on tweets

3 votes
2 answers
358 views

Deep Learning for Recommender System

3 votes
2 answers
10k views

One-Hot Vector representation vs Label Encoding for Categorical Variables

3 votes
2 answers
690 views

DIfferent learning rates converging to same minima

3 votes
1 answer
3k views

Principle behind seq2seq model's example in keras?

3 votes
1 answer
3k views

Applying convolutional neural network over text documents using 1-D tf-idf feature vectors

2 votes
1 answer
904 views

Best tool for text pre-processing, involving tokenization, lemmatization, stop-word removal, feature vector extraction?

2 votes
2 answers
1k views

Getting uniform distribution over topics from gensim's LDA?

2 votes
1 answer
393 views

Vectorizing equation in MATLAB

2 votes
1 answer
94 views

How to combine human-labelled data with user behavior data?

2 votes
1 answer
39 views

Good introductory reference for Bayesian Non-parametric (Dirichlet Process / Chinese Restaurant Process)

1 vote
0 answers
317 views

Scipy Sparse vstack memory error

1 vote
0 answers
8 views

Optimizing utility and square root of divergence via SGD

1 vote
0 answers
1k views

Can SMOTE be applied over sequence of words (sentences)?

1 vote
0 answers
81 views

Mean vs Sum of cost in theano

1 vote
1 answer
235 views

Reason for better performance of variants of SGD when local minimas of Neural Nets are equivalent?

1 vote
0 answers
92 views

$\chi^{2}$ kernel SVM performance issue

1 vote
2 answers
2k views

PCA on MNIST dataset results in very poor performance

0 votes
1 answer
100 views

Problem in constructing co-occurence matrix

0 votes
1 answer
600 views

Classifier on top of LDA topic vectors?

0 votes
0 answers
14 views

Policy Gradient training log-derivative un-normalized vs normalized objective

0 votes
1 answer
48 views

Gradients Exploding with Custom Gradient and 2 layer MLP

-1 votes
2 answers
2k views

Best way to tokenize tweet