Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 5 years ago.
Improve this question
i am exploring new architectures for LSTMs. i have looked into a few commonly used datasets, such as IMDB's movie reviews and sine waves, but haven't found a good generalizable dataset. if MNIST is the "hello world" for convolutional networks, then what would be the equivalent dataset for LSTMs?
You can check examples in which people use simpler models, like HMM and try running LSTM on them.
For example you can try running this POS tagging code (the pos_* part) from lazyprogrammer's course (here is a script that downloads and handles the data). This code contains models that use LSTMs on Tensorflow/Theano and also HMMs (and even logistic regression that does not take into account the sequential nature of the data).
Related
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 2 years ago.
Improve this question
I am looking for beginner Machine Learning Linear Regression problems. I searched in Kaggle, but couldn't find a proper one. Can you please suggest me a beginner problem from Kaggle, or from any other platform?
Thanks in advance.
Kaggle has tons of linear regression notebooks and datasets to learn from, most popular ones are probably about house pricing (given certain house features predict it's price).
Here's a new one I'm looking forward to solve:
Ben & Jerry's flavours and ratings ---> products.csv
The main goal would be predict wich ice cream flavours are better accepted based on it's ingredients.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 5 years ago.
Improve this question
Keras provides serveral pretrained models, like mentioned here:
https://keras.io/applications/
These applications are pretrained networks, like the following:
Xception
VGG16
VGG19
ResNet50
InceptionV3
MobileNet
I know that, VGG16 and VGG19 are fairly old networks in comparison to the others. However, is there a simply way to find out which model is the strongest or has the most weights?
One can look at the amount of layers by simpyly executing sth like:
model = applications.ResNet50(...)
print(len(model))
However, this does not give any information about the amount of weights provided, or the complexity (e.g. ResNet is residual, while VGG19 is not)
These models are implemented based on the corresponding original papers, which you can also see in the keras documentation.
For the detailed pros/cons of each model, you should read the papers. The newer model is not always the better in all applications.
For model size, you can see the number of weights in each layer by:
[w.size for w in model.get_weights()]
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 6 years ago.
Improve this question
My product is made in Python and I need Semantic Analysis for classification of sentences into questions, complaints, etc. Which is the best framework for the same?
I think the best approach would be, try several methods, cross-validated each method using a separate validation data set (or using K-Fold cross-validation) and pick the best one.
So as a starting point you can try:
Simple Logistic Regression using scikit-learn
Random Forest or Gradient Boosting Tree
Recurrent Neural Networks using Keras library.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 7 years ago.
Improve this question
use for drone quadcopter to track human body
This problem depend on many factors :
Computational resources.
Quality of images.
How much accuracy do you expect from the algorithm
By the way, the easiest way for implementing such algorithm is Cascade Classifier which is implemented in OpenCV. You can train your own model or you can use the trained model which exists in openCV files. This method support three feature types: HOG,LBP and HAAR. The base of this method is paper Viola and Jones published on 2001. The test time is near to online in an ordinary computer.
If you need more accurate method you can try DPM (deformable part models) based method. There are many released version of this method on the internet. The speed of detection is almost 2 HZ.
If you need more accuracy I suggest you to go forward with CNN (Convolutional Neural Networks). Of Course you need more computational resources (GPU or high spec CPUs)
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 9 days ago.
Improve this question
I am badly looking for a small size (around 50 nodes) link prediction dataset, with node attributes (preferably real-valued attributes).
The network can be directed or undirected (preferably directed), but the network preferably not be bipartite.
Of course I am looking for a free, ready to use dataset.
Perhaps related to a social network, author communications, etc.
Does any one knows a specific dataset? I really really appreciate showing me one.
This Google+ social networks with node attributes should be good for you. You can find it here: https://gonglab.pratt.duke.edu/google-dataset
The 'Social Network Analysis Interactive Dataset Library' at http://www.growmeme.com/sna/visual has over 150 datasets, and an ability to filter by directed/undirected and bipartite = true/false and whether community information is present (among other things).