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
0answers
22 views

Classify with `RandomForest` method

I try to run Classify with the RandomForestmethod, and when I set TreeNumber with a value more than 980, I get an error. Does ...
1
vote
2answers
64 views

How to assemble layers to perform different linear transformations on each column of matrix?

I have a matrix $A_{m×n}$ and I want to assemble a network that performs $n$ different trainable linear transformations $T_{p×m}(i), i\in {1,2,...n}$ on its corresponding columns, (i.e. $B^i = T(i)A^i)...
7
votes
1answer
154 views

Running Mathematica in 'SpouseMode'

In this previous question I looked into a deprecated capability of Mathematica from Version 2. Mathematica command that allows it to read my intentions Thanks to all for your answers. I note that ...
1
vote
1answer
38 views

Extract details from PredictorFunction object

For training data, the command Predict generates an object PredictorFunction, which can evaluate a prediction from variables. ...
1
vote
0answers
33 views

What is the preprocessor NumericalSequenceExtractFeatures?

When I use Classify on a dataset with inputs that are matrices with different row sizes (i.e., sequences), and I check the internals of the ClassifierFunction by running ...
0
votes
2answers
63 views
0
votes
1answer
38 views

How can I rescale data by a learnable constant in a neural network?

I'm working on a class of machine learning problems which fit functions from scalars to vectors. Let's suppose the output of this function is just a set of two-component vectors. I have found that my ...
0
votes
1answer
82 views

Is there any way to compile and export LearnedDistribution?

I use the LearnDistribution function to learn the distribution of some data. Then, I want to export some code to sample from that learned distribution. I tried to use Compile as follows ...
1
vote
1answer
53 views

ClassifierMeasurements returns strange errors

I am following the example listed on this page ResNet 50 to train a custom classifier and inspect the outcome with ClassifierMeasurements. My training set has 443 images from more than 30 classes. The ...
3
votes
0answers
39 views

Training a neural network with post-processed data [closed]

I want to fit a large number of functions over a vector space with a neural network. I have a particular architecture in mind, which is naturally broken into two parts: the first part consists of ...
0
votes
0answers
39 views

Can Predict/Classify/NetTrain be parallelized over multiple computers (kernels)?

A similar question was posted more than five years ago here and I was wondering if anything has changed and whether there is a way to parallelize Classify/Predict/NetTrain now. More specifically, ...
3
votes
0answers
31 views

extract dynamic values from video frames [duplicate]

I have a video recording the time and temperature during the experiment. I would like to ask whether it is possible for MMA to extract the above two values (highlighted in red boxes) from the frames ...
0
votes
0answers
30 views

How to give Classify a list of files on disk instead of importing them all at once?

I am trying to use Classify to train an image classifier on a dataset of 30k+ images. I followed this tutorial and created a list of the form {File[…]->class,…}. I can use NetTrain with this list, ...
6
votes
0answers
106 views

Extracting information from Classify

I have used Mathematica's automated Classify function: ...
5
votes
1answer
117 views

Loss function with regularization

The ML framework has a limited set of loss functions available. How can I extend this by creating my own custom ones? For example, for L2-regularized training, Mathematica recommends ...
3
votes
0answers
24 views

Assessing your own classifier function with ClassifierMeasurements or NetMeasurements

The functions ClassifierMeasurements and NetMeasurements expect objects that are created through ...
0
votes
1answer
101 views

Interactive Machine Learning App to make Predictions using Descriptors

I have developed a Machine Learning algorithm that uses 4 chemical descriptors to calculate a chosen chemical property. I would like to create an interactive app on Mathematica (using the manipulate ...
3
votes
0answers
81 views

Classify/NetTrain run indefinitely without output when using GPU

I am experimenting with Mathematica's Classify/NetTrain functions for the first time. When I don't set a TargetDevice option, Mathematica defaults to the CPU and everything works as expected. When I ...
4
votes
1answer
227 views

Complex numbers in neural networks

I am trying to construct a neural network which fits a collection of functions from (complex-valued) vectors to complex numbers. After constructing a suitable network, I was surprised to see that ...
2
votes
1answer
88 views

How to build an RNN with input as character but output a sequence of tokens?

Let’s assume I have “abbcab”-> {“Apple”,”Banana”}, “Bibb”-> {“Carrot”} so the output is a sequence of various length, but I can pad it to be the same length. My problem, how do I create a ...
2
votes
1answer
30 views

What's the difference between train and test evaluation modes of a BatchNormalizationLayer?

After creating a BatchNormalizationLayer: batchnorm = NetInitialize@BatchNormalizationLayer["Input" -> 3] We can evaluate it in "Test" or &...
1
vote
1answer
64 views

How is the loss computed from the batch and round?

This is cross-posted from the forum. I am trying to just reproduce the loss computed during training a very simple network. In this case the loss is just the standard L2 loss function. Start with some ...
2
votes
1answer
63 views

Copying Weights using NetTrain in Mathematica

I would like to implement the PPO algorithm - Reinforcement Learning - in Mathematica. And for that, I need to be able to copy network weights from say subnetwork NN1 to subnetwork NN2 as an update ...
3
votes
0answers
35 views

Can NetNestOperator take a non pre-defined number of iterations?

I'd like to Nest a particular NetChain inside a larger NetGraph for a random number of ...
12
votes
0answers
223 views

Trying to build a code to translate handwritten formulas using ML

I'm lazy writing equations in Latex so I want a code to translate handwritten equations. This question is related to an old experiment I'm reviewing during vacations, here. I'm trying to use ...
2
votes
0answers
27 views

Classify command option question

I'm using Classify to predict who is going to win a battle based on their strength. The input is something like {{"Name 1", Strength1},{"Name 2", Strength2},{"Name 3", ...
2
votes
0answers
57 views

Questions on NetMapOperator, NetNestOperator, NetFoldOperator [closed]

I've been playing around with the Higher-Order Network Construction functionality such as NetMapOperator, NetNestOperator, and <...
11
votes
0answers
188 views

Tutorial example NetTrain fails miserably with a GPU

I have been experimenting with GPU NetTrain on AWS now when Mma 12.2 supports remote batch jobs (I don't have an Nvidia GPU to try these things out otherwise). In ...
0
votes
1answer
58 views

Constructing Net problem

so I'm trying build a simple net that will help me find the winner in a competition. I would like to use as input "Name", "FA" and "Force", and obtain "Winner" ...
2
votes
2answers
96 views

how to implement training for UNET implementation on Wolfram Neural Net Repository?

My question is with reference to the U-NET implementation present on the Wolfram Neural Net Repository The construction notebook present on the page (link: http://...
15
votes
1answer
239 views

Minibatch Standard Deviation Layer

I'm reworking some of the GANs I originally made in TensorFlow2 to see if I can improve performance in Mathematica, and have been stuck on how to create a custom Minibatch Standard Deviation Layer. I'...
3
votes
0answers
72 views

Classify and Predict results that I don't understand

I have a list of rules that has as the left hand side the font size and a letter and for the right hand side the space in pixels between this letter and the following letter. The data is from a ...
1
vote
3answers
112 views

plotting plot $(- \infty, x]$ for any arbitrary $x$? [closed]

is it possible to plot $(- \infty, x]$ for any arbitrary $x$ on wolfram online? is it possible provide commands? I am trying to understand the concept of Vapnik-Chervonenkis dimension.
4
votes
0answers
72 views

How to train each layer in a Neural Network so they optimize different loss functions in an adversarial network?

Example NetGraph to illustrate the idea (Input is an online signal with a value between -1 and 1, Noise is Gaussian Centered at 0 and standard deviation 0.1, EvilNet is constrained to output a value ...
2
votes
1answer
75 views

Want neural net example of rules {vector->string}

I am using data samples from a multispectral color sensor for color classification as an exercise in beginning to learn about neural networks. I have succeeded with ...
2
votes
1answer
114 views

Help with creating the NetChain

I'm trying to train a network to take 3 integers and give an output = Max/Min. For example {10, 20, 30} -> 3. But I cannot get the setup correctly. I must be missing something. ...
1
vote
0answers
101 views

Machine Learning / Deep learning using Mathematica? [closed]

I am looking forward to the recommendation to learn ML/DL in Mathematica I know that there are plenty of resources web sites and books, MOOC to learn Machine Learning and Deep Learning mostly in ...
0
votes
1answer
59 views

multivariate Gaussian distribution with identity covariance

I want to draw Geometry (or contours) for multivariate Gaussian distribution with identity covariance matrix (or draw decision boundary). How this is possible via Wolfram's online at Here? Please ...
4
votes
1answer
114 views

How to use classify to separate lines and circles

I generated lines and circles: ...
3
votes
2answers
181 views

How to find explicit hyperplane in SupportVectorMachine

I am using the SupportVectorMachine classfier: e.g., (* let me use Linear kernel for simplicity *) ...
2
votes
1answer
43 views

Get layer types from Predict[trainingset, Method -> {“NeuralNetwork”}]

I am using the Predict-Function with the NeuralNetwork-method on some training data. But I cannot figure out the characteristics of the NN that is built, especially not the layer types. How can I get ...
0
votes
1answer
57 views

Binary Classify a Large Data Set using Deep Learning

I tried training this model: All even integers map to T and all odd ones map to F. I used 100 million training examples with Support Vector Machine as the method yet I got garbage for the test cases. ...
0
votes
1answer
54 views

Classify does not work with my training set [closed]

I tried using Classify. It gives the wrong answer even for training data. c = Classify[trainingset]; c[13] ...
1
vote
1answer
64 views

Recognizing letters in grid with TextRecognize

Here is the test image: You might recognize this as a Boggle board. I want to translate the image into a 4x4 array of letters. Not quite sure how to deal with rotated letters and ambiguous letters ...
3
votes
1answer
76 views

Fitted equation with Predict

Is there a way to know the fitted curved from the function Predict when choosing the linear regression method. I am using this data: ...
4
votes
1answer
106 views

How can I plot this one-dimensional Self Organizing (Kohonen) Map?

Mathematica used to have a package called NeuralNetworks that is not currently working. With that package, you could create a Kohonen or Self Organizing Map (https://en.wikipedia.org/wiki/Self-...
4
votes
1answer
80 views

Detecting Lines in Data

I have some data representing a vaguely periodic signal, here is a sample ...
1
vote
0answers
57 views

What are all the machine learning methods that can be used for Predict?

When I'm writing code for the Predict function, it allows me to choose what method I want to use. There are 7 options available from the drop-down after I type in <...
2
votes
0answers
75 views

Create New Type of Layer For Neural Network

I'm doing some work exploring modelling neural networks in which each neuron could represent a different type of physical system. What I want to do is, I think, quite different to what an ordinary ...
4
votes
1answer
225 views

Save neural network after training

I've written quite a few projects that involve training a neural network through the Classify and Predict functions, but every ...

1
2 3 4 5
11