Data Science Stack Exchange
Data Science Stack Exchange

Most Popular

more tags
1500 questions
23
votes
2 answers

What are kernel initializers and what is their significance?

I was looking at code and found this: model.add(Dense(13, input_dim=13, kernel_initializer='normal', activation='relu')) I was keen to know about kernel_initializer but wasn't able to understand it's significance?
thanatoz
  • 2,405
  • 4
  • 16
  • 39
23
votes
3 answers

What is the meaning of term Variance in Machine Learning Model?

I am familiar with terms high bias and high variance and their effect on the model. Basically your model has high variance when it is too complex and sensitive too even outliers. But recently I was asked the meaning of term Variance in machine…
Sociopath
  • 1,243
  • 2
  • 12
  • 27
23
votes
1 answer

How to add non-image features along side images as the input of CNNs

I'm training a convolutional neural network to classify images on fog conditions (3 classes). However, for each of about 150.000 images I also have four meteorological variables available that might help in predicting the classes of the images. I…
Josh
  • 487
  • 4
  • 8
23
votes
6 answers

Uploading images folder from my system into Google Colab

I want to train a deep learning model on a dataset containing around 3000 images. Since the dataset is huge, I want to use Google colab since it's GPU supported. How do I upload this full image folder into my notebook and use it?
chatbot_chakra
  • 341
  • 1
  • 2
  • 3
23
votes
2 answers

Why ReLU is better than the other activation functions

Here the answer refers to vanishing and exploding gradients that has been in sigmoid-like activation functions but, I guess, Relu has a disadvantage and it is its expected value. there is no limitation for the output of the Relu and so its expected…
Green Falcon
  • 14,058
  • 9
  • 57
  • 98
23
votes
5 answers

How to annotate text documents with meta-data?

Having a lot of text documents (in natural language, unstructured), what are the possible ways of annotating them with some semantic meta-data? For example, consider a short document: I saw the company's manager last day. To be able to extract…
Amir Ali Akbari
  • 1,393
  • 3
  • 13
  • 25
23
votes
4 answers

What is the difference between Inception v2 and Inception v3?

The paper Going deeper with convolutions describes GoogleNet which contains the original inception modules: The change to inception v2 was that they replaced the 5x5 convolutions by two successive 3x3 convolutions and applied pooling: What is the…
Martin Thoma
  • 18,880
  • 35
  • 95
  • 169
23
votes
3 answers

Pandas Dataframe to DMatrix

I am trying to run xgboost in scikit learn. And I am only using Pandas to load the data into a dataframe. How am I supposed to use pandas df with xgboost? I am confused by the DMatrix routine required to run the xgboost algorithm.
Ghostintheshell
  • 431
  • 1
  • 4
  • 7
23
votes
6 answers

Similarity between two words

I'm looking for a Python library that helps me identify the similarity between two words or sentences. I will be doing Audio to Text conversion which will result in an English dictionary or non dictionary word(s) ( This could be a Person or Company…
gogasca
  • 749
  • 2
  • 8
  • 17
22
votes
2 answers

NLP - Is Gazetteer a cheat?

In NLP, there is the concept of Gazetteer which can be quite useful for creating annotations. As far as I understand: A gazetteer consists of a set of lists containing names of entities such as cities, organisations, days of the week, etc. These…
AbtPst
  • 378
  • 1
  • 2
  • 9
22
votes
2 answers

How to increase accuracy of classifiers?

I am using OpenCV letter_recog.cpp example to experiment on random trees and other classifiers. This example has implementations of six classifiers - random trees, boosting, MLP, kNN, naive Bayes and SVM. UCI letter recognition dataset with 20000…
Mika
  • 323
  • 1
  • 2
  • 7
22
votes
2 answers

How to choose the features for a neural network?

I know that there is no a clear answer for this question, but let's suppose that I have a huge neural network, with a lot of data and I want to add a new feature in input. The "best" way would be to test the network with the new feature and see the…
marcodena
  • 1,667
  • 4
  • 14
  • 17
22
votes
3 answers

How do I create a complex Radar Chart?

So, I want to create a Player Profile Radar Chart something like this: Not only the scale of each variable different, but also I want a reversed scale for some statistics like the 'dispossessed' stat, where less actually means good. One solution…
Kunal Dharamsi
  • 323
  • 1
  • 2
  • 4
22
votes
3 answers

How to generate synthetic dataset using machine learning model learnt with original dataset?

Generally, the machine learning model is built on datasets. I'd like to know if there is any way to generate synthetic dataset using such trained machine learning model preserving original dataset characteristics? [original data --> build machine…
m-bhole
  • 323
  • 1
  • 2
  • 8
22
votes
1 answer

Lightgbm vs xgboost vs catboost

I've seen that in Kaggle competitions people are using lightgbms where they used to use xgboost. My question is: when would you rather use xgboost instead of lightgbm? What about catboost?
David Masip
  • 6,051
  • 2
  • 24
  • 61
1 2 3
…
99 100