Questions tagged [neural-networks]
Questions involving defining, training, executing, importing and exporting neural networks.
564
questions
0
votes
0
answers
34
views
How to treat small numbers in order to gain efficiency and precision in neural network algorithm?
Unfortunately I won't be able to provide a MWE, as it would be too big and complex, and this question will be based on pure semantics, basically (and I understand if this is impossible to answer in ...
0
votes
0
answers
30
views
What is the network structure of Ademxapp Model A1 Trained on Cityscapes Data in the Mathematica?
I want to implement the model (Ademxapp Model A1 Trained on Cityscapes Data) on my data for segmentation, so I need the partial structure of this model, can anyone help?
3
votes
1
answer
175
views
Q&A System using LLMSynthesize and Nearest
I'm looking for a Wolfram Q&A system that scales to 100k of text documents.
Using Mathematica's similarity search (e.g. Nearest) or vector database operations (...
3
votes
1
answer
61
views
NetGraph won't accept EmbeddingLayers of different n
Why doesn't this work:
...
1
vote
1
answer
126
views
Fitting smooth monotonic function (low number of points, irregular grid)
I want to fit data in the hope of obtaining an estimate for other data points (i.e. a good guess for the last 4 variables as a function of the first).
Example data:
...
1
vote
0
answers
45
views
Any image captioning networks available yet?
Looking for an image captioning network to run in a notebook. I didn't see any on the NN Repo. Has anyone imported one successfully?
3
votes
0
answers
198
views
Fourier neural operator using wolfram mathematica
Fourier Neural Operator (FNO) is a neural network-based approach that combines deep learning with the Fourier transform to solve partial differential equations. It leverages the power of neural ...
1
vote
1
answer
87
views
Extract the latent space learned from a Neural Network
I would like to visualize and cluster vectors learned in the latent space of a Neural Network.
I am trying to cluster audio tokens, but I don't know what they represent. So the task is to ...
4
votes
1
answer
68
views
Is there a way to extract the function used in NetEncoder[{"Function", ... }]?
Is there a way — programmatically and with documented functions — to extract the function used in a NetEncoder[{"Function",...}] type encoder? I want to ...
0
votes
0
answers
50
views
How could I draw a picture by connecting stars between them?
My idea is to try to make a program which would be able to trace a given picture in the sky, by simply connecting stars. Therefore, I have two questions.
Is it possible to convert the product of an ...
1
vote
1
answer
109
views
Generating molecules using a GAN in Mathematica
I have been unable to find any tutorials or examples of creating molecules using a Generative Adversarial Network (GAN) in the Wolfram language. It appears that the Selfies paclet was created to ...
5
votes
0
answers
152
views
Target Device->"GPU" Not Working For Machine Learning: LibraryFunction error
I'm running Wolfram Desktop version 13.2.1, and after downloading Visual Studio, Nvidia Toolkit version 12.1 and 11.2, and verifying that
...
0
votes
1
answer
38
views
Sampling a new random ValidationSet at each epoch during NetTrain
My understanding is that the NetTrain option ValidationSet ->Scaled[0.2] setting will randomly sample 20% of the training data at the beginning of the fitting ...
0
votes
0
answers
72
views
Neural network: Segmentation of water and not water area
Good morning everyone. I have a large dataset of photographs similar to the one attached. It would be my intention to train a neural network to recognise water and "non-water" zones. How ...
3
votes
1
answer
83
views
How to get the mathematical expression of a trained network?
When a network is trained, is it possible to get the corresponding mathematical expression?
For instance consider this simple network:
...
4
votes
0
answers
84
views
TrainImageContentDetector example aborts on GPU
I'm running v13.2.1 on Ubuntu and trying to run the built-in examples. But I see a "GPU memory exhausted" error on the first one in the docs for ...
1
vote
0
answers
87
views
What is that neural network?
I am teaching my comp to add naturals by creating a neural network:
...
2
votes
1
answer
134
views
How to add hidden layers and plot these?
I have a question regarding neural network graphs.
In R there is the following code where a user can add hidden layers with different number of nodes:
...
3
votes
1
answer
64
views
How to align the dimensions of Deconvolution in neural-net?
I tried to implement a NetGraph similar to UNet in Mathematica, but I found an error in the dimension.
...
3
votes
0
answers
184
views
Why Mathematica's Classify gives 100% accuracy on FashionMNIST dataset
Tested on Mathematica 13.2
...
0
votes
0
answers
43
views
Learning extra parameters of RBF Neural Network under the NN framework on high dimension data
It's easy to contruct a basic neural network like MLP and RBF by NetChain
MLP, RBF
My question is how can I obtain different $\Sigma$ and $\mu$ for each neurons, ...
12
votes
4
answers
1k
views
Text recognition - extracting table of text from image
I want to extract table from the image bellow as a list of strings. I tried the following but it does not work.
...
3
votes
0
answers
108
views
Implementation of Restricted Boltzmann Machines?
A Restricted Boltzmann Machine is a classical and basic neural net method in Pattern Recognition and Machine Learning.
We can easily find implementation in Matlab or Python, but are there any ...
4
votes
0
answers
94
views
How to get an AWS VM to run Wolfram with a GPU (or Azure for that matter)
I have a neural network application that is too big for my Mac desktop. I've been looking at using RemoteBatchSubmit to Azure as a solution. I've gotten it to work using the base VM provided by Azure. ...
16
votes
1
answer
481
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 ...
1
vote
0
answers
28
views
How to use Predict function with constraints on the output?
I have trained the Predict function with Method as "NeuralNetwork" to learn a function of an angle 0 < theta < 2 Pi, with period 2 Pi (the function returns a positive real number). I ...
2
votes
0
answers
56
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:
...
19
votes
4
answers
863
views
Improve scanned image with handwritten text for high-contrast printing: how it can be done with Mathematica?
I have a set of scanned documents with handwritten text which by default is printed with very low contrast. Here is an example (a part of a document):
...
3
votes
0
answers
203
views
GAN Using Graph Convolution Network
I am using the Pokemon GAN tutorial in:
https://blog.wolfram.com/2020/08/18/generative-adversarial-networks-gans-in-the-wolfram-language/
Where convolution blocks and deconvolution blocks are given by:...
17
votes
2
answers
969
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, ...
4
votes
0
answers
51
views
Training NetGraph with a 2nd order optician
I would like to train NetGraph using a quasi Newton algorithm rather than a first order stochastic gradient method. However, in NetTrain there are only such optimisers. Is there any way I can make ...
1
vote
0
answers
70
views
Why accuracy of Neural Network does not change as its structure is changed?
I have the following neural network:
...
5
votes
0
answers
114
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 ...
1
vote
0
answers
91
views
How to measure accuracy of a neural network?
I have this Neural Network for a specific data set:
...
3
votes
0
answers
113
views
Applying Super-Resolution to differently sized images
I would like to make some images larger and noticed that there is a page in the documentation for doing super-resolution using a network structure. It's called "A Model for Super-Resolution."...
4
votes
1
answer
101
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
...
3
votes
0
answers
74
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 ...
2
votes
1
answer
83
views
How to make the output of NetTrain obey constraints?
Imagine I have this
trained = NetTrain[LinearLayer[], {1 -> {0.1,0.7,0.2}, 2 ->
{0,0,1}, 3 -> {0.4,0.4,0.2}, 4 -> {0.1,0.0,0.9}}]
I want to ...
1
vote
1
answer
57
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 &...
6
votes
1
answer
182
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 ...
4
votes
1
answer
272
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
...
3
votes
1
answer
167
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, ...
2
votes
1
answer
137
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 ...
2
votes
0
answers
58
views
Neural Nets: Can the back propagation/deep dream step be computed within the Net itself
I am trying see if I can do a deep dreaming algorithm without exiting a neural net.
This Generalized Backpropagation for Neural Networks (e.g. DeepDream) has a nice discussion of using the ...
1
vote
1
answer
101
views
Is there a difference between ElementwiseLayer@Ramp and Ramp in NetGraph?
This is about neural net! I put what I want to ask in the picture! This is the code!
...
0
votes
0
answers
53
views
How to manipulate neural network output data?
I have a large list data for neural network training in the form
{x1 -> y1, … , xn -> yn}
Where the outputs $y_i$ is either 1 or 0 and the inputs $x_i$ are ...
2
votes
0
answers
41
views
EmbeddingLayer with variable input length is incompatible with LinearLayer?
EmbeddingLayer\[size, n\] trains a representation of a list of integers between 1 and n into a real vector of dimension ...
7
votes
1
answer
217
views
Exactly recreating image NetEncoder output
I need to run an exported NetChain in ONNX, surprisingly the model exports and runs successfully, but there's a discrepancy in the image loading stage (the NetEncoder'ing that must be written manually)...
3
votes
1
answer
97
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
31
views
Repeated calculation with neural network measurement slows down
I have a list of 200 neural nets nets0. I have to measure the output of several layers of each of them on a list of 1000 associations ...