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
4
votes
1answer
102 views

How to use classify to separate lines and circles

I generated lines and circles: ...
3
votes
0answers
76 views
+50

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
38 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
41 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
50 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
54 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
68 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
71 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
74 views

Detecting Lines in Data

I have some data representing a vaguely periodic signal, here is a sample ...
1
vote
0answers
54 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 <...
1
vote
0answers
62 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 ...
3
votes
1answer
106 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 ...
4
votes
0answers
118 views

Probem of Classify's Tree Method in Batch Predict

$Version 12.1.0 for Microsoft Windows (64-bit) (March 14, 2020) ...
0
votes
0answers
54 views

Neural network symbolic inputs and weights

If I create a neural network like, for example, so: ...
0
votes
0answers
49 views

Interpolated Hyperbolic tangent as a layer of a neural network

It is necessary to specify piecewise linear interpolation of the hyperbolic tangent. And substitute this function as a layer of a neural network. I tried a lot of things, please suggest your options.) ...
0
votes
0answers
57 views

Network training error InvalidJSON

I want to insert piecewise linear interpolation of the hyperbolic tangent into the neural network. An error occurs at the stage of training the network. trainingData: ...
4
votes
0answers
76 views

Seq2Seq RNN with an AttentionLayer

In many Sequence to Sequence machine learning tasks, an Attention Mechanism is incorporated. Before Transformer Networks, introduced in the paper: Attention Is All You Need, mainly RNNs were used to ...
1
vote
0answers
19 views

Retrain an existing ClassifierFunction with new data

Classify[] and Predict[] generate nice ClassifierFunnction, but it is not clear to me whether these can be retrained on new data, without the data originally used for training.
18
votes
4answers
400 views

Find best region to put text onto image

Given an image upon which you want to inset text, the question arises: What is the best sub-region to place text? For example, given a background image I want to find the rectangle in the image (...
7
votes
1answer
153 views

Decoding Music in Staff Notation using ImageIdentify

I wrote this Code fragment Which is a E (quarter) note in Treble Clef. Instead Mathematica simply classified it as a "musical note" Can we do better?
3
votes
1answer
188 views

How to paraphrase text?

I'm looking to train or use pre-trained models in order to re-phrase text. Are there any natural language models in the Wolfram Neural Repository (or elsewhere) that can be used to paraphrase text? ...
2
votes
1answer
2k views

GPU support on latest MacBook Pro, especially for deep learning

I'm thinking about getting some new top of the line computer hardware, specifically a MacBook Pro from Apple. These have AMD Radeon Pro 5500M GPUs, which while a bit slower than something like an ...
3
votes
0answers
53 views

Clarity on Classify's ClassPriors option

I'm looking for clarity on Classify's ClassPriors option, and I've listed some specific questions below. According to the documentation: ClassPriors is an option ...
2
votes
1answer
63 views

Using Predict to fill in missing data

I am attempting to use Predict[] to fill in the missing data in the dataset below; ...
9
votes
1answer
173 views

How to implement BlazeFace?

BlazeFace is a lightweight and well-performing face detector tailored for mobile GPU inference. It runs at a speed of 200-1000+ FPS on flagship devices. How to implement BlazeFace in Mathematica?
9
votes
2answers
262 views

Can I use Mathematica to generate candle scents?

I found this blog (which is highly entertaining). It has an interesting post where the author uses the GPT-2 neuro-network with candle scent training data to generate new candle scents. The AI comes ...
4
votes
0answers
88 views

Neural network for a simple game?

I'm taking a class that is based on the Mathematica coding language, and we must do a 6-week final project. I am considering coding a neural network for a simple game like 2048, pacman, snake, etc. ...
4
votes
0answers
53 views

Is there a way to get the decision trees used by machine learning methods like `RandomForest`?

I was looking at a tutorial of SimFin, a new German-based financial data provider. There is a nice example of machine learning using sklearn in python. The package ...
4
votes
1answer
101 views

Adding Noise in Neural Net via ElementwiseLayer

I am trying to add noise to a neural net to train a denoising autoencoder. I don't want to pre-calculate the noisy data. Rather, I'd like the noise be applied via a function using the ElementwiseLayer....
1
vote
0answers
28 views

Training with GPU and tuning parameters with ParallelTable

We intend to train a neural network. It has a hyperparameter, such as the learning rate. We want to compare the training results of different hyperparameters. Our computer has two multi-core CPUs and ...
2
votes
2answers
84 views

Usage and meaning of “ProbabilityHistogram”

When doing a classification one can determine the ClassifierMeasurements to get Information about the classifier. I now wanted to get a histogram of the computed probabilities for a classifier. Maybe ...
2
votes
0answers
56 views

Fuzzy Logic and Neural Networks

Is anyone working on building a Fuzzy Logic module that can be used for the output of Neural Networks? Thank You Michel
6
votes
0answers
147 views

How can I prevent errors with ReplicateLayer[]?

I am trying to build a NetGraph[] that takes input of the form {{0.6},{0.6},...,{0.8},{0.8}} and multiplies the last sequence ...
1
vote
0answers
144 views

is the code of this reinforcement learning example correct?

I am trying to learn reinforcement learning from an article on Wolfram.com, and after several days I still cannot quite get everything right. Now I wonder about the correctness of a piece of code ...
2
votes
1answer
67 views

How can I use ThreadingLayer to perform operations with layers of different dimmensions?

Is there a way that I can achieve subtraction between a scalar and a vector within NetGraph[], similar to what happens when I perform ...
3
votes
1answer
76 views

Controlling learning rate decay or cyclic learning rate in Mathematica's neural nets

I am using Mathematica's NetTrain[] function for training neural nets. There is a way to set the learning rate (LearningRate and ...
7
votes
1answer
81 views

Logistic Regression classifier in Versions 12 vs 11.3

There is a mysterious "LogisticRegression" method in MMA, which could be applied as a substitution for missing multinomial logit functionality. In version 11.3 I had the following simple 3-category ...
14
votes
3answers
434 views

Importing a grid of numbers from an image (sudoku like)

Can anyone see a way to import a grid of numbers from http://www.mit.edu/~puzzle/2019/puzzle/lantern_festival.html into Mathematica? TextRecognize doesn't seem ...
1
vote
0answers
43 views

How to run least confident based uncertainty sampling

This is a rather open-ended question. I am currently using Classify to run a Random Forest and I would like use an active learning algorithm on it. The most conducive would be least confident based ...
2
votes
1answer
152 views

Rounding the output Vector of a Neural Network layer to prepare it for the next layer

I am attempting to Round up the output Vector of a Neural Network layer to prepare it for the next layer Ex. Layer output {.1.,2.2,3.3} and I need it to be a Vector of Integers for the next layer. I ...
3
votes
1answer
158 views

How can I normalize a dataset relative to data already given previously?

Some scientific libraries, like Scikit-Learn for Python are able to create normalizing/standardizing functions based on data that is previously given. Looking at the documentation for ...
6
votes
1answer
203 views

How to find similar words from the provided list?

Let's say I have created a list of words that are acceptable in a certain context. list = {...}; Now given a new or some existing word from the list I want to ...
0
votes
2answers
90 views

What's wrong with FindFormula after I set the value of x from 100 to 1000?

The first code here. x = 100; list4 = Table[i^2, {i, 3, x}]; list5 = Table[3 i, {i, 3, x}]; Transpose[{list4, list5}] // FindFormula Output: ...
0
votes
1answer
58 views

Machine Learning with Manipulate [closed]

My code pops up error, and it take lots of time before Mathematica finish this. What's the problem here? Can anyone improve my code here? ...
0
votes
0answers
39 views

CNN model for CIFAR-10?

Does anyone know of a pre-trained model for the CIFAR-10 dataset? I've seen how to get the dataset(s) using various flavors of ResourceData["CIFAR-10"] But I ...
9
votes
1answer
416 views

Deep learning outperforms in symbolic integration and ODE?

There comes a new paper on arXiv (arXiv 1912.01412, Deep Learning for Symbolic Mathematics by Guillaume Lample, François Charton) claiming that a deep learning model outperforms Mathematica a lot in ...
4
votes
1answer
123 views

Generating “fake persons” with Mathematica?

Similar to this site, does Wolfram have some capacity to generate "fake humans" (for a cool demonstration)?
4
votes
0answers
197 views

Image-based reinforcement learning with neural networks

After seeing that "OpenAIGym" is not exactly supported on Windows and playing around with https://www.wolfram.com/language/12/neural-network-framework/train-an-...
0
votes
0answers
27 views

BatchNormalizationLayer instead of data prep

I've trained a neural net to match nx7x5 matrices to nx1 scalars; the n is a number of elements in a sequence. To get a good match I have to do some data prep; basically do a ...
0
votes
0answers
19 views

NetTrain::invindim3 error msg when train a simple CNN

My data is 1*5*5 matrix with label 0 or 1 like below: {{{1, -1, 0, 0, 0}, {0, 1, -1, 0, 0}, {-2, 3, 3, -2, -2}, {1, 2, 1, -2, -2}, {-1, -1, 0, 1, 1}}} -> 1 ...

1
2 3 4 5
11