Questions tagged [neural-networks]

Questions involving defining, training, executing, importing and exporting neural networks.

109 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
20
votes
0answers
264 views

Implementing Contextual Bandits

The multi-armed bandit problem (MAB) is a classic in Reinforcement learning. Now that Mathematica version 12 finally has support for Reinforcement learning: Here's a nice "mnist example" for training ...
19
votes
0answers
601 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 ...
11
votes
0answers
483 views

How to speed up calculations on big symbolic matrices?

this is my first time posting something on a community of the StackExchange platform, so please feel free to correct me if I'm doing something wrong. :) Additionally you should probably know that I'm ...
10
votes
0answers
435 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 ...
9
votes
0answers
100 views

How to implement graph neural networks in Mathematica?

Graph neural networks are useful for prediction tasks like predicting walks. In python I use DeepGraph typically, but I'm wondering what can be done in the new Version 12. Here's a nice introduction ...
8
votes
0answers
107 views

Slow down training many neural networks (Bug?)

I am working on something in which I need to train a neural network many times with slightly different training data. I noticed that after many training runs the input rate had dropped significantly. ...
8
votes
0answers
148 views

Remote kernels, Neural Networks and formatting of Dynamic content

Bug fixed in 11.2 I have a few GPU/CPU 'loaded' Linux boxes in my lab, used largely for rendering. I want to compare the new 11.1 Neural Network stuff to some Tensorflow things we do here. Of course, ...
8
votes
0answers
368 views

What are the software requirements to train neural networks on GPU?

It seems that GPU training in Mathematica has some additional requirements on the software. For example, when I run this example on a Linux system, I get the following errors ...
8
votes
0answers
339 views

Use of new machine learning capability for search problems (reinforcement learning)

I work with search algorithms, often of an adversarial nature, and want to understand how to apply Mathematica's machine learning capabilities, especially those new in version 11, to this type of ...
7
votes
0answers
449 views

Train your own CycleGAN style translator

I have a set of images (a few hundred) that represent a certain style and I would like to train an unpaired image to image translator with CycleGAN. I'm looking for a tutorial on how one would do ...
7
votes
0answers
309 views

How to implement the same function use *Layer function?

Reading YOLO method to detect object in the image(paper),I want to train this tiny-VOLO v1 on Mathematica,but the special loss function is very difficult to write. ...
6
votes
0answers
64 views

How can one train a Neural Network in Mathematica such as to recognise and count all occurrences of a certain custom category in an image?

I'm trying to use Mathematica for the following task: (1) Get an aereal view of a certain area in Mongolia (2) Count the number of plots that contain houses, and the number of plots that contain ...
6
votes
0answers
134 views

Export ImageCases to Python?

I’d like a tutorial on how to export a bounding box detector network to mxnet, (for bonus points: convert to Tensorflow), and then get it running correctly in python! Some related questions exist for ...
6
votes
0answers
244 views

How to train a bounding box detection model?

Apparently, this still isn't possible in v12? I'd like to add a new class to one of the standard object detection architectures. Consider the YOLO v2 detector from the Neural Net Repo. ...
6
votes
0answers
111 views

Optimize a network topology?

I'd like to know if one can use optimization function like Maximize[] or BayesianMaximize[] to optimize the hyper-parameters of ...
5
votes
0answers
77 views

Gradient of neural network output with respect to input

Context: I'm studying adversarial attacks on neural networks. These attacks are grouped into targeted, where a legitimate input is changed by some imperceptible amount and the new input is miss-...
5
votes
0answers
42 views

Possible NetTrain[] memory leak when training in GPU

I've just moved to Mathematica 12.0 (from 11.3) and sometimes NetTrain[] will fail with the following error: ...
5
votes
0answers
128 views

NetTrain on a UNet with a NVidia Quadro P5200 GPU

I am trying to train a UNet on my laptop (Lenovo P72) and I obtain the following error when I use NetTrain on it: CompiledFunction::cfta: Argument {Mean[LibraryFunctionError[LIBRARY_FUNCTION_ERROR,...
5
votes
0answers
70 views

Can I extract symbolic expression of neural network loss function?

Once we create a neural network with NetChain in Mathematica, can we extract the loss function in the symbolic form for Mathematica to play with symbolic manipulations using Mathematica's built-in ...
5
votes
0answers
86 views

How to extend ImageCases?

I was very excited to see ImageCases being documented in version 12. But I immediately desired a mechanism for adding more entities to ...
5
votes
0answers
122 views

What's BayesianMinimization and related functions based on?

Is it specified anywhere what the backend is for the Bayesian optimization related functionality in Mathematica v11? I'm specifically referring to the Bayesian* ...
5
votes
0answers
424 views

How to train a visual attention model?

In version 11.1 there is a new layer type SequenceAttentionLayer[]. I'm interested in how might this be used to train a recurrent visual attention model (see the ...
4
votes
0answers
64 views

Improving NetChain for Physical Data

I am trying to improve my NetChain to better predict physical data from the industrial standard for water/steam published by the IAPWS. Basically, this industrial ...
4
votes
0answers
104 views

Visualizing and Understanding CNN with Mathematica

The famous 2013 paper from Zeiler and Fergus "Visualizing and Understanding Convolutional Networks" proposes a method to understand the behavior of CNN using one (or more) DeConv networks coupled with ...
4
votes
0answers
50 views

How to implement external memory for the “memory augmented neural network”?

I am trying to implement the memory-augmented neural network using MMA 11.3. The memory-augmented neural network in based on the paper here. There are implementations using ...
4
votes
0answers
58 views

Candidate sampling for softmax neural networks in mathematica

Though I've been using mathematica for a few years, I've never really delved into its ML capabilities (except for the occasional clustering). I'm curious if anyone who has some experience using ...
4
votes
0answers
92 views

How to do broadcast in NeuralNetworks?

In normal case, we can multiply the tensor by the scalar, vector like this: ...
4
votes
2answers
211 views

Why doesn't NetTrain use GPU as TargetDevice?

I have a NetTrain call with the following parameters: tNet = NetTrain[inVecs -> outVecs, TargetDevice -> "GPU"]; But ...
4
votes
0answers
83 views

Capsule Network reconstruction layer

I am experimenting the capsule network, using the architecture provided here: Capsule Network in Mathematica Deep Neural Network Repository While I can figure out what the network do following the ...
4
votes
0answers
76 views

In neural network, how to force the NetTrain to use full batch gradient descent instead SGD?

In a neural network, I want to use full batch gradient descent instead of SGD. Currently, I am using code like this (you can see that I forced BatchSize to be the ...
4
votes
0answers
107 views

How to explain overfitting?

SeedRandom[0]; X = RandomInteger[{1, 5000}, {100000, 50}]; Y = RandomInteger[{0, 1}, 100000]; For net1 and ...
4
votes
0answers
135 views

YOLOv3 Netmodel?

I see that YOLOv2 is on the Wolfram net repo, but has anyone ported the new YOLO version 3 architecture into Mathematica?
4
votes
0answers
317 views

Using Machine Learning techniques for text-analysis

I am analysing a bunch of tweets and I want to understand which political party the authors support. Let say, for example that I have five parties labelled by a number: ...
4
votes
0answers
177 views

NetTrain throws internal error with large images as input (GPU)

I am training a convolutional Network with a dataset consisting of Images of the same size on my GPU (200x100 pixels, GTX 1080Ti). The images are previously resized with ...
4
votes
0answers
159 views

NetTrain with External GPU?

I'd like to use the new Neural Networks functionalities in v11 on my Macbook Pro, unfortunately, most macs do not have the supported Nvidia cards. However, there is the option for using an external E-...
3
votes
0answers
51 views

NetGraph copying by reference

I have a GAN defined like so: GAN = NetGraph[{"gen" -> generator, "dis" -> discriminator}, {"gen" -> "dis"}]; My question is if I use NetTrain on ...
3
votes
0answers
80 views

How to access coefficients and gradients of neural networks?

I would like to test optimization for neural networks for that I need to access the weights/bias of the different layers and the derivatives of the output or a loss function with respect to these ...
3
votes
0answers
90 views

NetModel fails to load a pre-trained model: Very Deep Net for Super-Resolution, in 11.3

I'm trying to run VDSR in Mathematica 11.3 on windows. My situation is: in: NetModel["Very Deep Net for Super-Resolution"] out: ...
3
votes
0answers
107 views

Can you train ImageClassify model with multiple GPUs correctly?

After some testing, I still cann't train with two GPU in Windows 10. But I can train with Mathematica 11.3 in Ubuntu 16.04 with two graphics card GTX 1080 The problem is, If I use two card to train, ...
3
votes
0answers
45 views

Layer states of NetBidirectionalOperator

I want to define a NetBidirectionalOperator version of this network, how do I access states of forward and backward net with ...
3
votes
0answers
106 views

Can someone help me to understand sequence-to-sequence transformation using (Wolfram-specific) recurrent neural nets?

I've been learning about recurrent neural networks lately and I think I'm starting to get the basic idea of how they work. I'm particularly interested in the sequence transformation capabilities of ...
3
votes
0answers
171 views

Is is a bug when importing MXNet model?

There is a trained net:model.zip Using Python to make prediction: ...
3
votes
0answers
229 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). ...
3
votes
0answers
506 views

Why “Inception V3 Trained on ImageNet Competition Data” have 1001 outputs?

There are 6 pre-trained models on ImageNet in NetModel. ...
3
votes
0answers
107 views

How can I monitor the process of neutral network training?

In the Linux command line,type wolfram then use NetTrain[net, mnist, Automatic, "LossEvolutionPlot"] can get the ...
3
votes
0answers
272 views

radial basis function network in Mathematica 11

I wanted to compare some (pre-existing) Python code I have for Radial basis function (neural) networks (RBFNN) for the goal of function approximation, with what I could obtain with Mathematica 11.0. ...
3
votes
0answers
169 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/...
2
votes
0answers
54 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 ...
2
votes
0answers
82 views

Hessian of a loss function for a neural netwrok

Is a way to calculate the Hessian of the loss function in Mathematica. It's easy to define a loss function for neural nets but I couldn't figure out how to calculate the Hessian(more precisely I ...
2
votes
1answer
77 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 ...