Questions tagged [neural-networks]

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

Filter by
Sorted by
Tagged with
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 ...
3
votes
1answer
97 views

How do I create my own activation function in NetChain in Mathematica?

I want to have my own activation function, say a quadratic function, instead of Tanh, or Sigmoid etc. in Mathematica. How do I insert it in NetChain? e.g., how will the below code look for a new ...
0
votes
0answers
60 views

TargetDevice->“GPU” takes no effect in prediction of Classify and ClassifierMeasurements?

I can train the model with GPU via method->"NeuralNetwork" in Classify. I'm on Mathematica 12.0 and the problem also happens in 11.3. Is this a bug since 11.1 to 12.0? In training, GPU is faster ...
10
votes
1answer
381 views

Bug in Mathematica 12 neural networks?

I recently downloaded Mathematica 12, and I'm experiencing a curious failure in neural networks that had earlier worked. This failure I will demonstrate with the NN in "Classifying Data with Neural ...
5
votes
0answers
88 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 ...
1
vote
0answers
41 views

Use of Normal with layers and plots

In documentation of ConstantPlusLayer we find ...
6
votes
1answer
91 views

Compute neural network loss over sliding windows?

I am trying to use the structural similarity index, which is defined in terms of a computation over sliding windows, as a neural network loss function. Obviously one can get a sliding mean using a <...
6
votes
1answer
132 views

Bug in EmbeddingLayer?

...
6
votes
1answer
146 views

How to load trained RNN in MXNet?

No problems with CNN ...
0
votes
0answers
51 views

Compatibility Nvidia and Mathematica 11.3 [duplicate]

I am wondering about the compatibility between Mathematica 11.3 (Windows or Linux) and the Nvidia Quadro P5200 provided in the ThinkPad P72. Can I be sure that Mathematica will be able to detect and ...
2
votes
1answer
68 views

How can I have two neural network layers act as the input to one layer?

When using NetGraph[], I am try to specify the connections between 3 layers like so: NetGraph[{...some layers...},{...{2,3}->4}] But I receive the following ...
2
votes
1answer
56 views

Where to find information about models, data and labels used by Image/AudioIdentify?

I am thinking about using Mathematica 12's ImageIdentify and AudioIdentify functions for an interdisciplinary research project. The social science part of it requires to describe a little bit the ...
1
vote
0answers
19 views

Is there an inverse type function to SequenceLastLayer[]?

I am working on a text based autoencoder, and was happy to see I can feed a variable length text sequence into my network and use SequenceLastLayer[] after a GatedRecurrentLayer[] to only get the ...
1
vote
0answers
65 views

Is Wolfram Cloud going to support GPU training? [duplicate]

Is Wolfram Cloud going to support GPU training? Is there any other possibility for training a neural net (in WL) on a cloud like AWS, Floydhub, or so? I think this concerns lots of people.
2
votes
1answer
79 views

3D Deconvolutional Layer

I noticed that one of the mxnet APIs (Gluon) includes a 3D Deconvolutional Layer. However, mathematica currently only allows up to 2D deconvolutional layers (see here). Can one somehow implement a 3D ...
1
vote
0answers
66 views

Neural Network stick in an unlearned state

Background: I want to apply a net to mapping from xyY color space to Munsell. The mapping in freely downloadable as a 5000+ entries table. I transformed the table data so that the Munsell Hue is given ...
0
votes
0answers
70 views

Learning weights during training

Let's assume I have a net so the loss function is composed from 3 components: $C_1, C_2, C_3$, and each component is multiply by its weight $(w1, w2, w3)$. The weights should be a function of $\beta$,...
4
votes
0answers
121 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 ...
3
votes
1answer
103 views

NetPortGradient returns “floating-point overflow” for this simple network

Consider this simple network that computes the following function: $$ \left\{ \begin{matrix} xy & \mbox{if} \;x,y>0 \\ 0 & \mbox{otherwise} \end{matrix} \right.$$ The net looks like: <...
51
votes
5answers
8k views

Mathematica command that allows it to read my intentions

In version 2.0 of Mathematica there was a command, ReadProgrammerIntentions[ ] which allowed it rapidly compose code that could solve problems simple to complex, ...
0
votes
0answers
23 views

Replace part of a net with NetReplacePart with another net with different number of outputs

I have a net with a nested sub-net like ...
6
votes
0answers
260 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. ...
5
votes
1answer
237 views

Creating a generator function for a large data set for a neural network

After reading documentation on Training on Large Data Sets, I am still at a loss on how to create a generator function, to read a batch of 1000 of this ...
4
votes
1answer
113 views

How to improve spelling in the Deep Speech NetModel?

There is only one NetModel for speech recognition. As is stated in the network repository, models trained with CTC loss have difficulties in producing correct spelling: ...
2
votes
1answer
29 views

Can I get the “Image Size”, etc. from a NetEncoder in an existing net from the Repository?

I want to get the details about the input used to train a net in the Net Repository, in my case "LeNet Trained on MNIST Data". I can get its decoder by: ...
0
votes
1answer
220 views

NetGraph/Model for BERT?

Does anyone know of a way to get the BERT model working for word embeddings in Mathematica? Doesn’t seem to be available on GitHub or the Wolfram Net Repo...
1
vote
1answer
55 views

Error NetTrain::invencin: Invalid input when training a neural network [closed]

I've build a Deep neural network with various variables: ...
9
votes
1answer
306 views

How do I implement masked Softmax?

Consider: input = {1, 2, 3}; mask = {1, 0, 1} Classic Softmax: SoftmaxLayer[]@input {0.0900306, 0.244728, 0.665241} ...
2
votes
1answer
85 views

How to provide an RNN various type of inputs?

I'm trying to build an RNN in Mathematica. My window is only 2 but the variables are of different types: ...
4
votes
0answers
53 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 ...
0
votes
1answer
110 views

Robust face detection

FindFaces doesn't work when people are far away from the camera. I'm looking for a single accurate method of detecting one or more people in an images, at all ...
1
vote
1answer
88 views

Training a Neural Network on a rule of List

Is is possible to train this format of data? ...
12
votes
0answers
439 views

Matlab Neural Network Toolbox vs Wolfram Neural Network Framework [closed]

Can anyone who has worked with both Matlab and Mathematica provide some comparison of how the Matlab Neural Network Toolbox compare to that of Mathematica. Mathematica as far as I understand is a ...
1
vote
0answers
55 views

Loading machine learning library without enabling my discrete Nvidia GPU? [closed]

I've asked a similar question [here]. I cannot use some of the machine learning modules without enabling my discrete Nvidia GPU. My setup: Ubuntu 16.04 on a Dell XPS-15 9560 Intel i7 CPU with 8-...
1
vote
0answers
53 views

NetTrain with GPU crashed

I tried to run NetTrain with TargetDevice->"GPU", and Mathematica crashed. I got the following message: When I executed ...
2
votes
0answers
53 views

“Learning” to parameterize Hermitian matrices with a basis using neural networks

I'm interested in using neural networks to "learn" how to write down Hermitian matrices, specifically those which are defined over spaces with a specific tensor product structure. The simplest example ...
8
votes
0answers
109 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. ...
1
vote
0answers
109 views

customized complex loss function to a neural network

My general question is how can I add a customized and complex loss function to neural network? I have to address this issue ASAP, because I did not find any good examples that can do it. In the loss ...
3
votes
2answers
297 views

Answer multiple choice questions

FindTextualAnswer isn't working for me here: ...
3
votes
1answer
62 views

Specify input ports with NetGraph for network within a network

I have a network with two input ports ("a" and "b"). I want to use this net within a bigger network. The problem is that I cannot find a syntax to specify to which input port the previous layers of ...
1
vote
1answer
79 views

Neural network not training due to function not loading

I'm trying to train a neural network on Mathematica 11.3, but NetTrain won't work and gives the follwoing error: ...
11
votes
1answer
409 views

Creating an indicator function in a neural network

I am working on implementing the loss function of the Yolo version 2 object detection network and building from the construction notebook in the Wolfram Neural Network repository Yolo Version 2 so I ...
0
votes
0answers
39 views

how to train a neural network [duplicate]

I have developed the following code, but I would like to train a neural network so that it can recognize all the dog breeds, integrating many images in order to have a high probability that the ...
2
votes
1answer
73 views

Issue deploying a FormPage using Classify

I developed this code that allows me to recognize what breed is the dog in the inserted image (for the time being developed only for five breeds of dogs), however, when I go to insert the image in ...
6
votes
1answer
199 views

Symbolic Neural Networks in Mathematica

Mathematica is very well known about its symbolic capabilities/functionality. Heavy users usually say that “everything is a symbolic expression”. Does this principle apply to neural networks? If not, ...
2
votes
0answers
30 views

Graphic scaling of neural network SummaryGraphics

Same funky scaling occurs when dragging the SummaryGraphics with the mouse; so, the issue is in the graphics itself not in the ...
1
vote
0answers
61 views

Monitoring the Training Progress through PutAppend

I would like to export the round loss during my model training for each training round. Currently, I am using the way shown in the Documentation Center around TrainingProgressFunction and PutAppend: <...
9
votes
2answers
120 views

Controlling the randomness of DropoutLayer

How can I control the randomness of DropoutLayer in order to get the same result after each execution? For example: ...
3
votes
1answer
120 views

Identify emotions from a drawn face using machine learning?

Can someone tell me how you could modify this code so that it recognizes more facial expressions? ... thanks for the help. ...
1
vote
1answer
98 views

What do the numerical values obtained from “FeatureExtraction” mean and what are their applications?

I started a self study on machine learning with mathematica recently. I have seen the power of predict and classify. I am particularly impressed with "FeatureExtraction" function but I really want to ...