All Questions

Filter by
Sorted by
Tagged with
239
votes
11answers
222k views

What are deconvolutional layers?

I recently read Fully Convolutional Networks for Semantic Segmentation by Jonathan Long, Evan Shelhamer, Trevor Darrell. I don't understand what "deconvolutional layers" do / how they work. The ...
208
votes
8answers
256k views

How to set class weights for imbalanced classes in Keras?

I know that there is a possibility in Keras with the class_weights parameter dictionary at fitting, but I couldn't find any example. Would somebody so kind to ...
198
votes
9answers
259k views

What's the difference between fit and fit_transform in scikit-learn models?

I'm a newbie to data science, and I do not understand the difference between the fit and fit_transform methods in scikit-learn. ...
195
votes
6answers
204k views

Micro Average vs Macro average Performance in a Multiclass classification setting

I am trying out a multiclass classification setting with 3 classes. The class distribution is skewed with most of the data falling in 1 of the 3 classes. (class labels being 1,2,3, with 67.28% of the ...
190
votes
35answers
30k views

Publicly Available Datasets

One of the common problems in data science is gathering data from various sources in a somehow cleaned (semi-structured) format and combining metrics from various sources for making a higher level ...
167
votes
13answers
219k views

K-Means clustering for mixed numeric and categorical data

My data set contains a number of numeric attributes and one categorical. Say, NumericAttr1, NumericAttr2, ..., NumericAttrN, CategoricalAttr, where ...
154
votes
5answers
95k views

What is the “dying ReLU” problem in neural networks?

Referring to the Stanford course notes on Convolutional Neural Networks for Visual Recognition, a paragraph says: "Unfortunately, ReLU units can be fragile during training and can "die". For ...
147
votes
17answers
120k views

Best python library for neural networks

I'm using Neural Networks to solve different Machine learning problems. I'm using Python and pybrain but this library is almost discontinued. Are there other good alternatives in Python?
142
votes
4answers
82k views

When to use One Hot Encoding vs LabelEncoder vs DictVectorizor?

I have been building models with categorical data for a while now and when in this situation I basically default to using scikit-learn's LabelEncoder function to transform this data prior to building ...
142
votes
1answer
185k views

Difference between isna() and isnull() in pandas

I have been using pandas for quite some time. But, I don't understand what's the difference between isna() and isnull(). And, ...
140
votes
6answers
119k views

When to use GRU over LSTM?

The key difference between a GRU and an LSTM is that a GRU has two gates (reset and update gates) whereas an LSTM has three gates (namely input, output and forget gates). Why do we make use of GRU ...
139
votes
5answers
154k views

The cross-entropy error function in neural networks

In the MNIST For ML Beginners they define cross-entropy as $$H_{y'} (y) := - \sum_{i} y_{i}' \log (y_i)$$ $y_i$ is the predicted probability value for class $i$ and $y_i'$ is the true probability ...
136
votes
6answers
188k views

How to draw Deep learning network architecture diagrams?

I have built my model. Now I want to draw the network architecture diagram for my research paper. Example is shown below:
124
votes
18answers
115k views

How do you visualize neural network architectures?

When writing a paper / making a presentation about a topic which is about neural networks, one usually visualizes the networks architecture. What are good / simple ways to visualize common ...
119
votes
15answers
115k views

Python vs R for machine learning

I'm just starting to develop a machine learning application for academic purposes. I'm currently using R and training myself in it. However, in a lot of places, I have seen people using Python. What ...
112
votes
11answers
64k views

Why do people prefer Pandas to SQL?

I've been using SQL since 1996, so I may be biased. I've used MySQL and SQLite 3 extensively, but have also used Microsoft SQL Server and Oracle. The vast majority of the operations I've seen done ...
106
votes
12answers
186k views

Train/Test/Validation Set Splitting in Sklearn

How could I split randomly a data matrix and the corresponding label vector into a X_train, X_test, X_val, y_train, y_test, y_val with Sklearn? As far as I know, ...
102
votes
10answers
102k views

Choosing a learning rate

I'm currently working on implementing Stochastic Gradient Descent, SGD, for neural nets using back-propagation, and while I understand its purpose I have some ...
100
votes
12answers
104k views

SVM using scikit learn runs endlessly and never completes execution

I am trying to run SVR using scikit learn ( python ) on a training dataset having 595605 rows and 5 columns(features) and test dataset having 397070 rows. The data has been pre-processed and ...
100
votes
5answers
56k views

Why do cost functions use the square error?

I'm just getting started with some machine learning, and until now I have been dealing with linear regression over one variable. I have learnt that there is a hypothesis, which is: $h_\theta(x)=\...
99
votes
2answers
76k views

Training an RNN with examples of different lengths in Keras

I am trying to get started learning about RNNs and I'm using Keras. I understand the basic premise of vanilla RNN and LSTM layers, but I'm having trouble understanding a certain technical point for ...
98
votes
1answer
264k views

How to get correlation between two categorical variable and a categorical variable and continuous variable?

I am building a regression model and I need to calculate the below to check for correlations Correlation between 2 Multi level categorical variables Correlation between a Multi level categorical ...
91
votes
12answers
16k views

How big is big data?

Lots of people use the term big data in a rather commercial way, as a means of indicating that large datasets are involved in the computation, and therefore potential solutions must have good ...
88
votes
8answers
114k views

When should I use Gini Impurity as opposed to Information Gain (Entropy)?

Can someone practically explain the rationale behind Gini impurity vs Information gain (based on Entropy)? Which metric is better to use in different scenarios while using decision trees?
88
votes
3answers
48k views

Backprop Through Max-Pooling Layers?

This is a small conceptual question that's been nagging me for a while: How can we back-propagate through a max-pooling layer in a neural network? I came across max-pooling layers while going through ...
86
votes
4answers
73k views

Advantages of AUC vs standard accuracy

I was starting to look into area under curve(AUC) and am a little confused about its usefulness. When first explained to me, AUC seemed to be a great measure of performance but in my research I've ...
79
votes
5answers
50k views

Time series prediction using ARIMA vs LSTM

The problem that I am dealing with is predicting time series values. I am looking at one time series at a time and based on for example 15% of the input data, I would like to predict its future values....
78
votes
10answers
266k views

ValueError: Input contains NaN, infinity or a value too large for dtype('float32')

I got ValueError when predicting test data using a RandomForest model. My code: ...
77
votes
9answers
31k views

Data scientist vs machine learning engineer

What are the differences, if any, between a "data scientist" and a "machine learning engineer"? Over the past year or so "machine learning engineer" has started to show up a lot in job postings. ...
76
votes
6answers
107k views

strings as features in decision tree/random forest

I am doing some problems on an application of decision tree/random forest. I am trying to fit a problem which has numbers as well as strings (such as country name) as features. Now the library, scikit-...
76
votes
4answers
32k views

How are 1x1 convolutions the same as a fully connected layer?

I've recently read Yan LeCuns comment on 1x1 convolutions: In Convolutional Nets, there is no such thing as "fully-connected layers". There are only convolution layers with 1x1 convolution kernels ...
74
votes
2answers
64k views

When to use (He or Glorot) normal initialization over uniform init? And what are its effects with Batch Normalization?

I knew that Residual Network (ResNet) made He normal initialization popular. In ResNet, He normal initialization is used , while the first layer uses He uniform initialization. I've looked through ...
69
votes
7answers
79k views

Open source Anomaly Detection in Python

Problem Background: I am working on a project that involves log files similar to those found in the IT monitoring space (to my best understanding of IT space). These log files are time-series data, ...
68
votes
2answers
8k views

Are Support Vector Machines still considered “state of the art” in their niche?

This question is in response to a comment I saw on another question. The comment was regarding the Machine Learning course syllabus on Coursera, and along the lines of "SVMs are not used so much ...
66
votes
11answers
35k views

What is dimensionality reduction? What is the difference between feature selection and extraction?

From wikipedia, dimensionality reduction or dimension reduction is the process of reducing the number of random variables under consideration, and can be divided into feature selection and ...
64
votes
6answers
37k views

When is a Model Underfitted?

Logic often states that by underfitting a model, it's capacity to generalize is increased. That said, clearly at some point underfitting a model cause models to become worse regardless of the ...
62
votes
8answers
77k views

Clustering geo location coordinates (lat,long pairs)

What is the right approach and clustering algorithm for geolocation clustering? I'm using the following code to cluster geolocation coordinates: ...
61
votes
9answers
9k views

Tools and protocol for reproducible data science using Python

I am working on a data science project using Python. The project has several stages. Each stage comprises of taking a data set, using Python scripts, auxiliary data, configuration and parameters, and ...
61
votes
7answers
56k views

In supervised learning, why is it bad to have correlated features?

I read somewhere that if we have features that are too correlated, we have to remove one, as this may worsen the model. It is clear that correlated features means that they bring the same information, ...
61
votes
5answers
33k views

Adding Features To Time Series Model LSTM

have been reading up a bit on LSTM's and their use for time series and its been interesting but difficult at the same time. One thing I have had difficulties with understanding is the approach to ...
60
votes
5answers
148k views

Convert a list of lists into a Pandas Dataframe

I am trying to convert a list of lists which looks like the following into a Pandas Dataframe ...
59
votes
5answers
72k views

RNN vs CNN at a high level

I've been thinking about the Recurrent Neural Networks (RNN) and their varieties and Convolutional Neural Networks (CNN) and their varieties. Would these two points be fair to say: Use CNNs to break ...
58
votes
3answers
19k views

What is the difference between “equivariant to translation” and “invariant to translation”

I'm having trouble understanding the difference between equivariant to translation and invariant to translation. In the book Deep Learning. MIT Press, 2016 (I. Goodfellow, A. Courville, and Y. Bengio)...
58
votes
5answers
25k views

Latent Dirichlet Allocation vs Hierarchical Dirichlet Process

Latent Dirichlet Allocation (LDA) and Hierarchical Dirichlet Process (HDP) are both topic modeling processes. The major difference is LDA requires the specification of the number of topics, and HDP ...
58
votes
5answers
50k views

Neural networks: which cost function to use?

I am using TensorFlow for experiments mainly with neural networks. Although I have done quite some experiments (XOR-Problem, MNIST, some Regression stuff, ...) now, I struggle with choosing the "...
57
votes
8answers
14k views

Why do internet companies prefer Java/Python for data scientist job?

I see a many times in job description for data scientist asking for Python/Java experience and disregard R. Below is a personal email I received from chief data scientist of a company I applied for ...
57
votes
10answers
55k views

Machine learning - features engineering from date/time data

What are the common/best practices to handle time data for machine learning application? For example, if in data set there is a column with timestamp of event, such as "2014-05-05", how you can ...
56
votes
4answers
54k views

Why mini batch size is better than one single “batch” with all training data?

I often read that in case of Deep Learning models the usual practice is to apply mini batches (generally a small one, 32/64) over several training epochs. I cannot really fathom the reason behind this....
55
votes
5answers
105k views

Cross-entropy loss explanation

Suppose I build a neural network for classification. The last layer is a dense layer with Softmax activation. I have five different classes to classify. Suppose for a single training example, the <...
55
votes
7answers
33k views

Cosine similarity versus dot product as distance metrics

It looks like the cosine similarity of two features is just their dot product scaled by the product of their magnitudes. When does cosine similarity make a better distance metric than the dot product? ...

15 30 50 per page
1
2 3 4 5
538