Stack Exchange Network

Stack Exchange network consists of 174 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
Join us in building a kind, collaborative learning community via our updated Code of Conduct.

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

1
vote
0answers
21 views

How to ask FindClusters to return the loss function value in the output?

I have some data points pts as below:- pts = BlockRandom[SeedRandom[123]; RandomReal[1, {100, 2}]]; Now I want to separate ...
0
votes
0answers
20 views

How to change the formulae of FeatureExtraction?

I have a feature extraction function fe, which gives me n/0.816497 as the output of fe[{1}]:- ...
6
votes
1answer
295 views

Why is SVM unable to separate linearly separable data?

I have two sets of data, namely blue and yellow. I manually added a point {8, -3} to the blue data. ...
3
votes
1answer
66 views

How to reconstruct the result of FeatureExtraction?

For the below code for Mathematica 11.3, I got {-0.153792, 1., 1.} as output. ...
-1
votes
0answers
24 views

How to force FeatureExtraction to extract specific number of features?

I have two FeatureExtraction functions as below:- ...
0
votes
1answer
67 views

Problem of Low Accuracy of NeuralNetwork Method in Classify MNIST 11.3

The accuracy is extremely low... even after changing a lot of options of Method... Other methods' result is fine and normal, 0.80 accuracy like LogisticRegression. ...
4
votes
0answers
61 views

Value for output of layer is inconsistent (implementing SqueezeUNET from Keras)

I'm attempting to implement this neural network in WL: https://github.com/lhelontra/squeeze-unet/blob/master/squeezeunet.py which is a variant of the SqueezeNet network that does image segmentation. ...
2
votes
0answers
49 views

Why is the output of the Embedding layer so non-linear?

I have 2 nets, i.e. net1 (i.e. LinearLayer) and net2 (i.e. ...
1
vote
1answer
88 views

How to generate a training set in an automatic way?

This question is related to my previous item where arithmetic with machine learning was considered. The results of the Predict command were not good because of a ...
2
votes
1answer
45 views

Custom NetEncoder

I've been trying to train an RNN on some data that I pre-processed externally and saved to disk. My dataset is too large to fit in memory and is additionally varying in shape. Looking for a way to do ...
1
vote
0answers
60 views

Why Method -> “NeuralNetwork” does not work for me? [closed]

Mastering my Machine Learning, I try arithmetic: ...
5
votes
1answer
58 views

Why would a symmetric image have an asymmetric PoolingLayer-Gradient Image?

I have a symmetric image img. For simplicity, I would use the below image as my example: ...
3
votes
0answers
37 views

In neural network, how to force the NetTrain to use full batch gradient descent instead SGD?

In a neural network, I want to use full batch gradient descent instead of SGD. Currently, I am using code like this (you can see that I forced BatchSize to be the ...
5
votes
1answer
62 views

Which, if any, external machine learning libraries are used by Predict[]?

It's pretty much all in the title -- I suspect that Wolfram uses some standard (perhaps open-source) libraries in their machine learning functions, and I am curious as to what they are. I am ...
3
votes
1answer
42 views

How to apply the layer of sigmoid function in neural network?

I saw an article How to build a simple neural network in 9 lines of Python code and want to reconstruct the result in Mathematica. I tried the below codes:- ...
5
votes
0answers
41 views

Regarding Gaussian Process in Predict function

The following code is exactly copied from the documentation on Predict using Gaussian Process. ...
3
votes
0answers
34 views

How to NetTrain only N batches?

I'd like to train a neural network for only a specified number of batches, that is for only part of an epoch (or TrainingRound). I've tried using the ...
3
votes
1answer
44 views

Predict[] Application Timing

I trained a Predict and when I look at PredictorInformation it says evaluation time is less than 1 millisecond per example. ...
2
votes
1answer
43 views

Extract neural network model from ClassifierFunction

I'm very new to Neural Networks and Mathematica 11 (I used MMA8 some time ago) and I'm trying to learn about NN using Mathematica. I'm using MMA 11.2 in a Rapsberry Pi (yes, I know that doing NN in a ...
2
votes
1answer
76 views

What does NetMapOperator do?

Recently, I have become addicted to Mathematica's support for neural networks. As I learn those commands that are prefixed with "Net", I can't tell the difference between using ...
2
votes
0answers
67 views

Does Mathematica auto update something causes error load old-version model?

I've trained a NN model by NetTrain with Mathematica 11.3.0, and I can load the model correctly to predict. My model is saved by .mx format. After few months, I cann't load the model correctly. ...
5
votes
0answers
51 views

How to make the clustering result of version 11.2 and 11.3 same?

I was doing clustering analysis in version 11.2, with codes like below, and then got 12 clusters as the output: ...
4
votes
1answer
91 views

Deep Learning SummationLayer does not support varying dimensions on Linux server

I am trying a recurrent network in Linux server using MMA 11.3. The network structure is as follows: ...
4
votes
0answers
85 views

How to explain overfitting?

SeedRandom[0]; X = RandomInteger[{1, 5000}, {100000, 50}]; Y = RandomInteger[{0, 1}, 100000]; For net1 and ...
1
vote
1answer
35 views

How can I see the predictor function that Mathematica produces?

I am trying some basic machine learning with Mathematica. I am wondering if I can see the function that Mathematica produces for a training set. I give the following example: trainingset = {1 -> 1.3, ...
1
vote
0answers
41 views

Measurement of properties of custom classifying algorithm

I am interested in measuring my classifier algorithm. Therefore I look for something similar to ClassifierMeasurements, where I can put my predictions result and ...
5
votes
1answer
83 views

How to cluster a set of images?

I have a set of images (imgset) as Clearly, the classification list should be ...
1
vote
1answer
55 views

Issue fine-tuning a simple embedding network

I'm trying to learn an embedding on Cifar-10 by finetuning ResNet-50 with a few added layers: ...
3
votes
1answer
129 views

Detecting a pattern in a time series with a Neural Network

I new to working with Neural Networks and I want to detect a pattern in a time series and return some measure of the certainty/uncertainty when a pattern has been detected: ...
2
votes
1answer
67 views

How can I reproduce the result of AgeEstimation model in MXNet-Python?

How can I reproduce the result of AgeEstimation model in MXNet-Python? here is my repo about MXnet-Python codes to load Mathematica Models. I found in this codes, AgeEstimation is very challenging. ...
3
votes
0answers
179 views

Train your own CycleGAN style translator

I have a set of images (a few hundred) that represent a certain style and I would like to train an unpaired image to image translator with CycleGAN. I'm looking for a tutorial on how one would do ...
3
votes
0answers
67 views

YOLOv3 Netmodel?

I see that YOLOv2 is on the Wolfram net repo, but has anyone ported the new YOLO version 3 architecture into Mathematica?
8
votes
1answer
172 views

Dilation on 3D Images?

I need to apply a dilated convolution to a 3D image, but dilation values greater than 1 are not currently supported in v11.3: ...
3
votes
0answers
56 views

Can someone help me to understand sequence-to-sequence transformation using (Wolfram-specific) recurrent neural nets?

I've been learning about recurrent neural networks lately and I think I'm starting to get the basic idea of how they work. I'm particularly interested in the sequence transformation capabilities of ...
2
votes
0answers
88 views

Fashion segmentation with a neural net?

I would like to train a network that can parse clothing: Does anyone know of a fashion segmentation network with or without pre-trained weights available that I can use in Mathematica? Update: I ...
0
votes
0answers
43 views

Memory management using blocking but in vain

I have trained a classifier named c and want to apply it to testing set. However, due to the huge size of testing set, I have to make prediction in blocks/groups to ...
6
votes
1answer
436 views

How can image segmentation from UNET be improved?

EDIT 2: code can be found @ https://github.com/alihashmiii/UNet-Segmentation-Wolfram EDIT 1: applying Binarize to the masks after resizing helps to ensure the data for mask is binary I have made an ...
3
votes
2answers
71 views

Derivative of rectified linear unit in Mathematica?

I am following the artificial neural networks literature and apparently the latest trend is to use the rectified linear units (ReLU) as the activation functions for each neuron. I tried to take the ...
3
votes
1answer
113 views

Tutorial on net surgery?

I'm trying to replace the "fc1000" layer in a NetModel, what am I missing here: ...
3
votes
1answer
75 views

How exactly does NetTrain use a ValidationSet (can we reuse it as TestSet)?

Typically when you train a model you have three sets of data: training, validation, and testing - and they can’t be mixed, i.e. you can’t use images from one in the other. I want to know if the ...
10
votes
0answers
275 views

How to plug holes in an Image (with partial convolutions)?

NVIDIA recently published a new way to reconstruct images with holes. They use a new type of convolutional layer which is described in the paper Image Inpainting for Irregular Holes Using Partial ...
9
votes
1answer
118 views

NetEncoder for images of “Varying” dimension?

I'm looking for someway to do what this syntax "should" do: NetEncoder[{"Image", Automatic, ColorSpace -> "RGB"}] /@ imgs; The documentation states that ...
3
votes
1answer
43 views

Validation failed for ConvolutionLayer message?

I have a simple fully convolutional network and I'm trying to figure out why I get this error NetChain::valfail: Validation failed for ConvolutionLayer: kernel size 3*3 plus padding size 0*0 cannot ...
6
votes
1answer
311 views

FindFaces in Mathematica 11.3

I just upgraded to Mathematica 11.3. but now my FindFaces instructions do not work anymore. I guess they changed the syntax in 11.3. Here is the original code: <...
0
votes
0answers
35 views

How to modify the existing NetModel?

I want to use some existing network model resources, say the ResNet or VGG from the Wolfram Repository. Let say I import the ResNet by using the following code:- ...
3
votes
1answer
70 views

how to use CatenateLayer to connect nodes within a NetChain

EDIT: Looking closely at my network I have a similar problem of providing inputs to the CropLayer function. The output from the pooling layer (node 30) and node 87 (activation) should feed to the ...
3
votes
1answer
27 views

How to replace all activations in a NetGraph?

I'm trying to replace all activation layers of a certain type, there must be a simpler way to do this? ...
2
votes
0answers
37 views

Unable to create ClassifierMeasurements for NetGraph

I am trying to check the accuracy of a neural network by using ClassifierMeasurements. I take the MNIST as example:- Code for setting ...
2
votes
1answer
40 views

Unable to create NetGraph

I am trying to perform deep learning classification in Mathematica. I noted that I am unable to create NetGraph even when I just follow the simple steps in the help ...
1
vote
1answer
47 views

Specify NetEncode's tokenization model?

NetEncoder[{"Tokens"}] uses WordData indices to tokenize an input string. But is there a way to tell ...