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
53 views

Unable to replicate Predict/NeuralNetwork example from Help Pages

I am trying to replicate an example right out of the help manual (ref/method/NeuralNetwork). This example compares the convolutional NN versus a fully-connected NN....
68
votes
8answers
11k 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, ...
4
votes
0answers
73 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. ...
3
votes
0answers
37 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 ...
9
votes
2answers
234 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 ...
2
votes
1answer
51 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
121 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?
2
votes
1answer
110 views

UtilityFunction for actual and predicted values (machine learning)

In machine learning, the utility function for a classifier assigns the utility value to an actual value v(act) and a predicted value v(pred), typically e.g. in form of ...
3
votes
2answers
144 views

How to make Hinton diagrams

I just start studying machine learning with Mathematica and, I want to know how make Hinton diagrams. Can someone give an idea, please?
21
votes
0answers
704 views

How to ImageRestyle high-res images?

I’m running v12 now and ImageRestyle[] crashes for me on an image of size 1600 x 1200 pixels. All the examples in the documentation use images around 500 x 500 or ...
14
votes
0answers
511 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 ...
2
votes
0answers
218 views

How to generate names with a GAN?

I'd like a tutorial for text generation using GANs, specifically for names. I have a list of company names and would like the network to generate novel ones. This is one of the only few examples of ...
48
votes
3answers
3k 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 ...
4
votes
0answers
42 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
59 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
18 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
82 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 ...
0
votes
2answers
84 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: ...
5
votes
0answers
132 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 ...
8
votes
2answers
267 views

Resources to learn about Neural Nets using Mathematica?

I'm interested in learning about Neural Nets and I'd really like my instruction to be in Mathematica if possible. For instance, a tutorial like this one: http://neuralnetworksanddeeplearning.com/...
5
votes
1answer
315 views

Image Generator with a Neural Network (CIFAR-10)

As some of you may know, CIFAR-10 is a data base which has 60,000 images (which are 32x32 in size) of 10 different categories (airplane, dog, cat, frog, deer, bird, horse, ship, automobile and truck). ...
2
votes
0answers
41 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
1
vote
0answers
74 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
58 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
59 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
67 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
368 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 ...
2
votes
1answer
101 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 ...
1
vote
0answers
29 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 ...
3
votes
1answer
72 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 ...
4
votes
1answer
96 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 ...
9
votes
1answer
349 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 ...
0
votes
1answer
56 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
30 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 ...
1
vote
0answers
60 views
4
votes
0answers
185 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-...
4
votes
1answer
115 views

Generating “fake persons” with Mathematica?

Similar to this site, does Wolfram have some capacity to generate "fake humans" (for a cool demonstration)?
33
votes
4answers
1k 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 ...
10
votes
1answer
443 views

How to perform UMAP dimensionality reduction?

This new method UMAP looks to be better than TSNE, unfortunately it is not available as a dimension reduction method yet: Does anyone know if there exists an implementation of it in, or accessible ...
0
votes
0answers
20 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 ...
8
votes
1answer
391 views

How to find multi-word synonyms?

I’m looking to write a semantic distance function for phrases (5 words or less) that can map multi-word synonyms together. My domain is e-commerce fashion - here are some required examples for a ...
4
votes
0answers
97 views

How to get features for captioned images?

I have a lots of (image, text) pairs and would like to learn a feature extractor (or maybe a FeatureExtractorFunction) for a combined embedding. It seems that when given a list of these multimodal ...
8
votes
2answers
282 views

How to recreate this 3D plot?

In other languages, one can make a FeaturePlot3D-esque graphics where the inset images look realistically three dimensional. Meaning that they are smaller when farther away (and also hazier). So how ...
2
votes
0answers
71 views

How to train custom objects using YOLO in Mathematica?

I want to train few custom object using YOLO V2 architecture but not sure how to do this. I know that with the NetTake and NetReplace, this is achievable. Can someone point out me in the right ...
0
votes
0answers
14 views

Best approach to Save the BestValidationRound throughout training

I have a network that I would like to train.I would like at the end of training to be able to have the BestValidationRound, from all training Rounds. I would not want to have ...
3
votes
0answers
55 views

Net layer that replicates last element

I am trying to design a neural network layer that takes in an array of dimensions n x 100, and produces an array of dimensions ...
0
votes
1answer
99 views

Using a neural net to make predictions

I want to use a neural net to give predictions, but I am not sure where to start. I do know that I don't want to use the high-level Predict function. So what I ...
1
vote
0answers
45 views

Can LearnDistribution Train and Generate Images Without Defaulting To 256x256?

In spite of anything I try it seems the ConformImages[] function nested in the LearnDistribution[] function resizes images to 256x256. If I convert an image into its "Data" representation before ...
2
votes
1answer
59 views

Chaining NetGraphs

I have two NetGraphs, each with 3 different input ports ("Input","Random1","Random2"), the first with 2 outputs ("Output" and "Loss") and the second with one output "Final_Out". All I want to do is "...

1
2 3 4 5
10