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.

Filter by
Sorted by
Tagged with
0 votes
0 answers
15 views

which mxnet files can be deleted?

In an attempt to cleanup my limited space on my C: drive I found these huge file I guess some might be labeled as version 12.x related but I only use v13.1 Which files can be deleted? The total is ...
  • 3,710
9 votes
0 answers
90 views

Stable diffusion models in WL?

Are there any diffusion-based (text + image) -> image generation models available in Mathematica, Wolfram Repositories, or from third parties? In particular, I'm ...
  • 30.8k
6 votes
1 answer
116 views

Graph Convolution Network, molecule activity

I am trying to translate an example code for graph convolution network from Deep Learning for Physical Scientists: Accelerating Research with Machine Learning. Edward O. Pyzer-Knapp et. al. They have ...
  • 569
2 votes
0 answers
28 views

General hyperparameter searching?

I typically use naive random or grid search to choose them, but I'd like to ask if there are built-in or paclet-based methods that can help perform more principled general hyperparameter searches? For ...
  • 3,621
12 votes
0 answers
259 views

How to reconstruct 3d meshes from 2d images of a scene?

The new ImageStitch was nice functionality added in v13, but is there anything available for constructing meshes (with color textures) from a bag of 2D images (...
  • 30.8k
5 votes
2 answers
78 views

Which model behind SequencePredictorFunction?

Is the SequencePredictorFunction based on Hidden Markov Model? If so, how does the model estimate the number of hidden states?
2 votes
0 answers
47 views

Unable to Replicate an ANN Using the Output from Predict Function

I’m working on constructing an ANN. I first used the Predict function with the method “Neural Network” to determine the structure according to my data. This is the given output of the structure: ...
2 votes
0 answers
44 views

FeatureExtraction for TimeSeries giving errors

I'm trying to replicate this example using FeatureExtraction for TimeSeries. However, it's giving errors. Here's the code I've run: ...
  • 163
9 votes
1 answer
247 views

Labeling images for TrainImageContentDetector

I want to use TrainImageContentDetector on a directory of ~2k unlabeled images. I'm willing to put in the effort to label them, but I was never good at using "...
  • 3,621
8 votes
2 answers
278 views

A strategy to create good initial guess for Lorentzian model fit

I was preparing an answer for a question that got deleted, so I will post this anyhow. Given a set of data with a hump ...
  • 31.2k
1 vote
0 answers
56 views

How to measure a LearnedDistribution?

I would like to measure the qualities of a LearnedDistribution in general and with regard to test sets. The docs say that it takes an option ValidationSet, but ...
  • 3,621
0 votes
0 answers
32 views

What does standard deviation mean when using Predict[]?

I am using the Machine Learning function Predict[data, Method -> "DecisionTree"], and I am trying to get the most accurate measurement of its accuracy. ...
9 votes
1 answer
323 views

Diffusion probabilistic model in deep generative modeling

Diffusion Models (http://proceedings.mlr.press/v37/sohl-dickstein15.html and https://arxiv.org/abs/2006.11239) are generative models gaining popularity in the community of deep generative modeling, ...
3 votes
0 answers
118 views

TrainImageContentDetector gives very poor result on GPU compared to CPU

On the doc page of TrainImageContentDetector, there is an example of heart detector training. I tried this example with different TargetDevice and constrained the <...
  • 16.4k
4 votes
0 answers
82 views

Derivation from a network

how can I represent the derivative of a network (e.g. NetGraph or NetChain) as a network? I have tried it with FunctionLayer[] and NetPortGradient, but without success. I would be very pleased to ...
  • 81
4 votes
1 answer
53 views

"MoleculeFeatures" in FeatureExtractor

"MoleculeFeatures" is one possible Feature Extractor method. What molecule properties does "MoleculeFeatures" entail?
0 votes
0 answers
35 views

Identifying and tracking cluster elements in ClusterClassify for multiple time-steps of data

I have multiple time-steps of {x,y,z}coordinates data for some atoms. I would like to cluster the data for each frame and later identify how cluster compositions change and how each atom changes from ...
  • 569
1 vote
1 answer
77 views

Predict Function & Generating a Training Set

I am trying to use the Predict[] function to do a regression analysis. I have the data imported from a CSV and based on my past Python experience the libraries I used always have a slick way to take ...
  • 55
4 votes
1 answer
90 views

Does RandomArrayLayer implement the reparameterization trick?

I want to backpropagate through random operations (e.g. learn the mean and variance of a Gaussian random variable). I assumed that ...
  • 101
3 votes
1 answer
34 views

Retain Values in new column when Appending a column to an existing dataset

I am working on a basketball data set. I am trying to append a "Class" column which looks at the "Pos" column and assigns a 1 if a forward (C, PF, SF) or a 2 if a guard (PG, SG). I ...
6 votes
1 answer
116 views

Introductory material on machine learning?

Does Mathematica have a handbook or other introductory material on machine learning? Or are there any books on analyzing machine learning with Mathematica?
3 votes
0 answers
46 views

Create "PredictorFunction" with NeuralNetwork

I tried to construct a predictor for a continuous variable using neural networks, something like f(a,b,c,d,e) = x, trying to predict x for a given set of a,b,c,d, and e. The builtin ...
  • 31
2 votes
0 answers
81 views

FeatureExtraction[] for Text -- to normalize text or not?

The title pretty much captures my question. When I use FeatureExtraction[] for text, should I normalize text before parsing it through ...
  • 5,171
1 vote
0 answers
42 views

Is it possible to add new concept to ImageContents

I was hoping to use ImageContents to locate some specific objects in a series of images with a bounding box. However, ...
  • 3,862
3 votes
0 answers
68 views

Problem with Mathematica Relationship Building

When I enter the following to get Mathematica to open my pod door I get Could someone try and replicate this? Also, my name is not Dave and I throw my own error... ...
  • 6,978
2 votes
1 answer
65 views

How does mathematica generate FinalPlots

It is well known that after using NetTrain[net,dataset,All], a NetTrainResultObject is returned. This is an association, with a ...
  • 1,981
1 vote
1 answer
107 views

How to predict the future by machine learning past data?

The following is 1,094 days (Length@btcData) of Bitcoin prices. Among them, data for the first 985 days (Length@btctrain) were used for training, and data for the last 109 days (Length@btctest) were ...
  • 1,091
1 vote
1 answer
44 views

BasicRecurrentLayer with no bias and linear activation function?

Trying to design a small neural network for modeling a LTI system, I'd like to configure a BasicRecurrentLayer with these particular settings: No bias vector should be used (I've tried the option &...
  • 133
0 votes
0 answers
20 views

How to apply NetDecoder on each element in output?

I try to apply the NetDecoder on each output element but get an error. ...
4 votes
0 answers
196 views

How do I generate SMILES using machine learning in Mathematica

I am wondering if anyone has experience with generating molecules using machine learning in Mathematica. There are a bunch of papers these days with such applications/developments. For example, https:/...
  • 569
2 votes
1 answer
46 views

How many nearest neighbours in a classifier by default?

I've been running a classifier on my data with the 'NearestNeighbors' method. I've learned that I can specify the number of neighbours used with the following command: ...
  • 155
6 votes
1 answer
149 views

Unexpected high memory consumption using out-of-core NetTrain

I'm working on training a neural network on an image dataset. There are 14k images and each image contains 3x150x150 pixels. I have built a generator function following the approach in Training on ...
2 votes
4 answers
95 views

How to predict future samples from discrete samples of a low frequency signal?

Suppose I have discrete samples of a low frequency signal as in: For example: ...
  • 6,768
4 votes
1 answer
160 views

How to add doodles and sketches in a mandala

i discovered mathematica yesterday; and i've been playing with RandomMandala since. i also saw this question; and i really liked the second answer; but i like the ...
5 votes
0 answers
209 views

Any competitive speech-to-text models?

SpeechRecognize is not very useful compared to most voice transcription engines nowadays, simply too fragile and prone to errors. I use Otter.ai currently, is there anything competitive to that (or ...
  • 3,621
13 votes
1 answer
841 views

M1 Apple silicon ML performance

Testing out a new M1 Macbook pro with Mathematica 13.0.0. I verified that I used the correct version and it is running natively on ARM. Mathematica in general runs great, and much fast than on my ...
  • 131
4 votes
1 answer
173 views

Constructing neural networks from Keras example

I am trying to convert neural networks from a book to Wolfram language. The book has this example with the quote two layers of 10 neurons and a dropout of 0.2 for each ...
  • 569
3 votes
1 answer
56 views

Reuse same layer of Neural Network

I hope to wrap up ConvolutionLayer in a way so that it takes two inputs, does the same operation on those, and outputs their result respectively. For example, ...
  • 1,981
1 vote
0 answers
49 views

How to export the expandable graphs

So in Mathematica, neural network objects appear like this: This is rather boring, but if you click on the plus sign, it expands into a better graph: Which is ...
  • 1,981
1 vote
0 answers
92 views

Download Mathematica resource from another source [closed]

I want to do machine learning on Mathematica, however when I use obj = ResourceObject["CIFAR-10"]; to load the dataset, it shows errors after the ...
  • 1,981
17 votes
2 answers
294 views

How to export a ContentDetectorFunction for use in Python?

For text and images v13 introduces the ability to train detectors easy which result in ContentDetectorFunction's. To use these IRL we need to export to python's ...
  • 30.8k
2 votes
1 answer
76 views

CrossValidate for image classification with NetTrain

I am trying to set up transfer learning using instructions from this repository page on EfficientNet. I am able to perform a stand-alone training and testing using the instructions on that page. The ...
  • 569
0 votes
0 answers
40 views

Ranges of ANN predict values too narrow

I plan to train a neural network on a large dataset. Each example contain 16 parameters (inputs) and 1 output. A snapshot of the dataset looks like: net = ParallelTable[Parasets[[i]] -> {degraeffr[...
4 votes
0 answers
83 views

Exporting a DimensionReducerFunction

I need to run my DimensionReducerFunction in a standalone fashion outside of MMA. That is, without calling into a kernel or through an APIFunction. For example, ...
  • 30.8k
1 vote
0 answers
22 views

How is posterior distribution computed for various values of `Method` in the `Predict` function?

Assume I have some dataset to train a machine learning model on using Predict along with a test point x. ...
  • 233
0 votes
0 answers
50 views

How to change labels of confusion matrix in ClassifierMeasurements?

I have trained a classifier with classes A,B,C, and D, and when I use ClassifierMeasurements to plot the confusion matrix, the order of the labels is A,B,C,D. How can I change the order of the labels ...
0 votes
0 answers
53 views

Spliting training dataset in ANN training using NetTrain

I am training a neural network on large training dataset containing 25,525,200 examples. each example contain 15 parameters (inputs) and 1 output, such as Inputs 0.015,83.6,0.663,0.104,0.097,0.167,0....
3 votes
1 answer
79 views

Automated mapping between input and output columns of FeatureExtractorFunctions

This problem is about FeatureExtraction. It arose in the course of training a neural network where the data contains a mixture of nominal and numeric variables. Basically, my code looks like the ...
1 vote
0 answers
99 views

Increase the speed of Machine learning based on 'Predict'

I am training a ANN model with a large dataset (~million level) using Predict or NetTrain function. I do not have a GPU machine but have a server equipped with 16 CPU cores. How can I maximize the ...
1 vote
0 answers
83 views

How to solve ODEs using deep learning in Mathematica [closed]

I have a number of ODEs (58) with 16 parameters and 9 variables. I want to solve the ODEs to obtain the analytical relationship between the parameters and variables. It is obviously that the ODEs ...

1
2 3 4 5
13