Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [machine-learning]

Questions about machine learning functionality of Mathematica, for instance involving, but not restricted to, Predict, Classify, FindClusters and the various regression functions.

85
votes
1answer
10k views

Crack CAPTCHA using deep learning

Deep convolutional neural networks are very good at computer vision related tasks. Optical Character Recognition (OCR) is one important branch of computer vision. In fact, the convolution neural ...
67
votes
6answers
3k views

Q&A Mathematica v.11 Neural Networks: A comprehensive look at Layers, Net Functions, and pioneering into this [[experimental]] code

Motivation As Mathematica v.11 was released earlier this month with a host of new [[experimental]] functions and a limited number of examples on curated data that ...
62
votes
8answers
9k views

What are the Wolfram Language's relative strengths for machine learning?

I see a low use of Mathematica in Kaggle competitions. Why would one use the Wolfram Language versus R, Python, or Julia for machine learning? Besides prettier plots and the Manipulate function, ...
45
votes
2answers
2k views

Generalized Backpropagation for Neural Networks (e.g. DeepDream)

Is there currently any way to abuse NetTrain to maximize an arbitrary cost/utility -function in some hidden layer and/or even modify the input to increase neuron ...
43
votes
2answers
6k views

Object detection and localization using neural network

Four important computer vision tasks are classification, localization, object detection and instance segmentation (image taken from cs224d course): These four tasks are all built on top of the deep ...
38
votes
4answers
3k views

Generative Adversarial Network

Generative adversarial networks (GAN) is regarded as one of "the most interesting idea in the last ten years in machine learning" by Yann LeCun. It can be used to generate photo-realistic images that ...
38
votes
1answer
2k views

How to perform document classification (i.e. extracting topics from text)?

I need to build a multi-label text classifier. There are a bunch of techniques for doing this, and it's called automatic document classification. I'm trying to use the EM technique (expectation ...
36
votes
3answers
2k views

What is behind experimental function: FindFormula?

In version 10.2 there is a new experimental function: FindFormula[]. I suspect that a genetic programming algorithm (symbolic regression) is behind this new ...
34
votes
1answer
2k views

RNN in Mathematica?

Recurrent neural network is an important part of machine learning and its improved version: LSTM network is widely applied, but Mathematica seemingly is in lack of these two features and in my opinion,...
31
votes
1answer
1k views

How can I export my learned ClassiferFunction[] and PredictorFunction[]s?

Mathematica 10 provides beautiful high-level machine learning functionality. Sadly, the learned functions once created are rather opaque objects. I need to use them in other projects, so here is my ...
27
votes
1answer
2k views

How to export an MXNet?

I was hoping there was some way to generate the .params and .json file needed to define an MXNet model, from a network trained using NetTrain[] in Mathematica. I ...
26
votes
2answers
3k views

Using a Convolutional Neural Network for time series classification

In the recent new in Mathematica 11 webinar one user asked during the Q&A session wether the current implementation of neural networks in Mathematica 11 could be used for processing time series. ...
25
votes
1answer
1k views

How to monitor the process of Neural Network Learning

Main Problem I'm exploring the neural network in v11 and I would like to monitor the training progress in my own way instead of Mathematica's default way. So my question is, how to do this ...
25
votes
2answers
501 views

Frown for a sex change, or, how do I unbork the “FacialGender” classifier in 11.2?

The limits of machine learning. I thought the new "FacialGender" option for Classifier would be an amusing thing to explore. ...
24
votes
2answers
694 views

How to make a custom NN layer in Mathematica?

Is there a way to create our own custom layers for Neural Networks in Mathematica ? I suspect it should be possible, any pointers or directions on how to go about it? I am interested in ...
24
votes
0answers
1k views

Handwriting recognition with Mathematica

I am trying to teach Mathematica to read my handwriting. Since I don't want to ruin my reputation by showing my own handwriting, I am going to use a font called blackjack. Lets say this is a ...
23
votes
1answer
3k views

How can I detect if an image is of poor quality?

I need to filter out blurry or otherwise bad quality images from a set. I would like an efficient method to detect images that have any of the following three attributes: Out of focus or motion blur ...
20
votes
1answer
874 views

Biased results when using Method -> “RandomForest” in Predict

I am interested in using random forests for some prediction, so I have been using Predict. I find that "RandomForest" method ...
20
votes
2answers
1k views

How to know the internal algorithms of functions like Predict or Classify?

The document centre seems only explain how to use these functions, but just in an very brief way. I know Mathmatica is not open source, so we can not expect to see the code of the function, but are ...
19
votes
1answer
1k views

How to import a Tensorflow model?

I've trained a network in Tensorflow and have the checkpoint files, I'd like to if anyone has written a parser or importer to pull the evaluation graph and/or weights into Mathematica?
18
votes
0answers
156 views

Inefficient memory storage for Dataset

Why Dataset doesn't serialize its contents, isn't it the whole point? I expect it to behave similar to python's pandas.DataFrame,...
17
votes
4answers
804 views

How to use Mathematica to train a network Using out of core classification?

I see there is doc about how to train a network Using out of core image classification and this question.But the object is only image. I want to use a binary file as data(Sequence to Sequence case),...
16
votes
2answers
4k views

Machine learning. SVM algorithm

I want to work with machine learning in Mathematica. Are there any SVM algorithms implemented in Mathematica anywhere? Or any other algorithms for machine learning? With positive and negative database ...
16
votes
5answers
2k views

Recurrent neural network in 11.1 explicit examples?

I heard that RNN was implemented in Mathematica as of 11.1. Trying to search online, I find some general information about neural networks in Mathematica, or a list of related functions. My trouble is ...
16
votes
1answer
2k views

How to split a Dataset into training and testing for machine learning?

Suppose I have iris data In the Dataset Format. How to split the iris data Into training and testing for Machine learning? For example,Transform the data for Classify.
16
votes
1answer
1k views

Classify command in Mathematica 10

Where can I find documentation about the methods used in the Classify command in Mathematica 10? Specifically, how does the method ...
16
votes
1answer
923 views

How to implement a stateful RNN?

If the model is stateless, the cell states are reset at each example. With the stateful model, all the states are propagated to the next example. Stateful RNNs can learn the long sequences. For ...
15
votes
1answer
360 views

Rapid density estimation and rendering of decision regions

I would like to create an interactive demonstration using Manipulate[] that illustrates a fundamental concept in pattern classification and machine learning. This ...
15
votes
1answer
3k views

How to visualize a random forest classifier?

I'd like to recreate this visualization (from python) in Mathematica: I'm not sure how to extract the decision boundaries from a classifier with "Method" set to "RandomForest". Here's the code: <...
14
votes
2answers
2k views

Trainable WEKA segmentation of images

Is there a Mathematica equivalent of Trainable WEKA Segmentation as implemented in Fiji, the image processing software? A Google search did not return any relevant links. I attach the original image ...
14
votes
2answers
1k views

How to detect loops in a vector field?

Given a vector field and I'd like to detect if there are streamlines in closed patterns. For example, if the input is a vector field like this: ...
14
votes
2answers
940 views

How to do Independent Component Analysis?

The new experimental function in 10.3.1 DimensionReduce[], has the following three options for Method: ...
14
votes
3answers
695 views

Inverse of Interpreter[“Color”]: Convert a RGBColor to a natural language color name

What is the best way to create the inverse function of Interpreter["Color"]? That function takes a natural language color name like ...
14
votes
1answer
251 views

WLNet format incompatible between version 11.0 and 11.1

It seems that there are some behavior changes of neural network layers from version 11.0 to 11.1 that leads to the incompatibility of WLNet format. Consider this example: Network exported in 11.0 <...
14
votes
1answer
741 views

Implementing t-SNE (t-Distributed Stochastic Neighbor Embedding)

Context Six months ago @M.R. asked about an implementation of the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm by van der Maaten and Hinton (2008). (@M.R.'s question) @Alexey ...
14
votes
0answers
461 views

How to ImageRestyle high-res images?

Running v11.2 on Ubuntu 16, ImageRestyle[] crashes for me on an image of size 1600 x 1200 pixels. All the examples in the documentation use images around 500 x ...
13
votes
2answers
1k views

How to change NeuralNetwork options?

How can I manipulate the architecture and problems of a NeuralNetwork in Predict or Classify? For example, running the following ...
13
votes
3answers
1k views

Transform Dataset so it can be used as training set for Classify

Trying to learn the new Dataset features, I am playing with the iris dataset: ...
13
votes
2answers
2k views

How to train a convolutional neural net on images?

The functions Predict[] and Classify[] both have the option Method -> "NeuralNetwork", ...
13
votes
2answers
413 views

How to implement a triplet network with NetSharedArray?

In v11.3, NetSharedArray[] and NetInsertSharedArray[] give us a mechanism of sharing weights and biases across neural networks, ...
13
votes
1answer
259 views

Training Neural Networks on Cloud GPUs (Wolfram Cloud / AWS / Paperspace /etc)

I have spent a lot of time lately training neural networks. However, my poor laptop has only an AMD GPU, so I am stuck training these networks on the CPU. That means I get to train networks over ...
13
votes
1answer
1k views

Is there any decent deep learning library in Mathematica?

Deep Learning is the currently trending method in machine learning community. Some languages like python and matlab have some very convenient toolbox for deep learning. So is there any decent deep ...
12
votes
2answers
304 views

Classify / Predict: ensemble of classifiers / predictors

Mathematica has undocumented functionality of combination classifiers / predictors in ensemble. How to get access to this functionality? SeedRandom[1]; X = Table[ Join[ ToString /@ RandomReal[{...
12
votes
1answer
1k views

How do I configure the input and output layers of a neural network?

I'm confused about how to set some of the basic properties of a neural network structure using Classify. I'm trying to set the basic properties of a simple neural ...
12
votes
1answer
419 views

How to monitor the progress of training a classifier?

I've had p = Predict[x -> y] running for hours and I have now idea if I should kill it or not. I'm looking for some rough bounds for an estimate of how long <...
12
votes
2answers
549 views

Implementing a Neural Network

TLDR: I am implementing a neural net in Mathematica and need help with back propagation. This is purely for the joy of implementing a neural network with a functional programming language. If someone ...
12
votes
1answer
534 views

Neural machine translation model using deep learning

In Mathematica version 11.1, SequenceAttentionLayer is introduced to model attentions in the recurrent neural network. It has been shown that attention mechanism ...
12
votes
1answer
775 views

Configuring GPU for NetTrain

I currently have access to a system with two GPUs: GeForce GTX 1080 and Tesla K40c I would like to use this machine for training neural networks in Mathematica. When using the option ...
12
votes
1answer
811 views

How to visualize attention?

In the articles about sequence attention we can see images like this: Here we see that while translating from French to English, the network attends sequentially to each input state, but sometimes it ...
12
votes
2answers
405 views

Simple example of NetGraph running in MXNet?

There is an great example of exporting a NetGraph (that was trained in Mathematica) into the MXNet's format. However, I think there's a bug or something is wrong with the answer, because once ...