We’re rewarding the question askers & reputations are being recalculated! Read more.

Questions tagged [neural-networks]

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

Filter by
Sorted by
Tagged with
2
votes
0answers
59 views

Unable to create ClassifierMeasurements for NetGraph

I am trying to check the accuracy of a neural network by using ClassifierMeasurements. I take the MNIST as example:- Code for setting ...
2
votes
1answer
60 views

Unable to create NetGraph

I am trying to perform deep learning classification in Mathematica. I noted that I am unable to create NetGraph even when I just follow the simple steps in the help ...
1
vote
1answer
67 views

Drop output from a Neural Network

I have a simple net: ...
4
votes
2answers
172 views

NetTrain with multi-label data?

I'm attempting to do simple category recommendation on textual data. I have around 20k training samples of the form desc_String -> {tag1_String, tag2_String, ...}...
0
votes
0answers
69 views

NetEncoder, Neural Networks

I want to encode temporal data as an input for a neural net. Currently it takes in a vector of length inputLength. TemporalData ...
28
votes
1answer
2k views

How to export an MXNet?

I was hoping there was some way to generate the .params and .json file needed to define an MXNet model, from a network trained using NetTrain[] in Mathematica. I ...
8
votes
2answers
278 views

Can't import Gluon into mma

This is a simple DNN from Fast, portable neural networks with Gluon HybridBlocks: This is json file and params file of Gluon(MXNet) ...
3
votes
0answers
181 views

Is is a bug when importing MXNet model?

There is a trained net:model.zip Using Python to make prediction: ...
3
votes
1answer
132 views

Single Neuron Dream Example (from Markus van Almsick's Presentation WTC 2017)

I'm teaching myself about Mathematica 11.3 Neural Net capabilities, and I can't get a demonstrably previously working example to work. I've been trying for quite a while without success. In Martin ...
2
votes
1answer
68 views

NetDecoder broken for Input Depth 4?

I am trying to interpret a 4-tensor net output as a 3-tensor of class probabilities : ...
10
votes
1answer
222 views

Can one use NetTrain with two Nvidia GPUs?

I am thinking of buying another GPU to accelerate my training. Will I be able to call NetTrain with both GPUs ("TargetDevice"-> {"GPU", All})? Or would it be ...
1
vote
1answer
131 views

Using NetTrain with HDF5?

I have some nicely formatted training data in HDF5 files, i.e. the images and labels are serialized within the H5 file as groups and datasets. AFAIK NetTrain only ...
0
votes
0answers
105 views

Simulating oscillations in a neural network

I am trying to simulate the synaptic dynamics in a Feed-Forward system. The system is composed of a ring of $N_1$ presynaptic neurons and a single postsynaptic neuron. The presynaptic neurons are ...
0
votes
1answer
79 views

Struggling with understanding NetGraph result

I am novice in Neural Networks and particularly with its implementation in Mathematica. I am trying to understand the graphical result of NetGraph function but it results in non-classical displaying ...
2
votes
0answers
105 views

Visualizing Trained Filters

In the first convolutional layer of NetModel "Wolfram..." , the parameters of the filter are 64 (number of filters), and 112x112 (size). The last convolutional layer has 192 55x55 filters. What ...
3
votes
0answers
248 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). ...
12
votes
1answer
344 views

Using PredictorMeasurements with a neural net?

PredictorMeasurements doesn't work with NetGraph, here's an example: ...
2
votes
2answers
134 views

ElementwiseLayer with Piecewise?

I need a specific custom activation function; how can I implement it with Piecewise? This is what I've tried (using the recommendation from this question): ...
5
votes
1answer
170 views

Build this neural network layer (NoisyAnd) more elegantly?

I want to build the neural network in "Classifying and segmenting microscopy images with deep multiple instance learning". It is a fairly straightforward CNN, except that they define a custom layer ...
3
votes
1answer
86 views

Using NetGraph as FeatureExtractor?

I'd like to compute FeatureDistance between two images with a NetGraph: rs = NetModel["ResNet-152 Trained on ImageNet Competition Data"]; fe = NetTake[rs, {1, -3}] ...
6
votes
1answer
134 views

Is it possible to convert the result of NetTrain to a PredictorFunction?

I would like to use PredictorMeasurements on the result of NetTrain, but it says it expects a ...
13
votes
2answers
1k views

How to change NeuralNetwork options?

How can I manipulate the architecture and problems of a NeuralNetwork in Predict or Classify? For example, running the following ...
4
votes
0answers
339 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
1answer
85 views

Subtracting elements of vector in net

I'd like to implement the following function $f$ in a neural net: $$ f(i,j)=s_i-s_j $$ where $1\leq i,j\leq N$ are integers and the $s_i\in\mathbb{R}$ are learnable parameters. What's the best way ...
0
votes
0answers
70 views

Training speed of NetTrain on GPU

I have a model with NetTrain that works fine. However, as I increase the amount of training data, the number of inputs per second to my GPU drops very, very substantially. In fact, when I include all ...
8
votes
1answer
166 views

Audio equivalent of CurrentImage

Unfortunately, there is no CurrentAudio[] function yet. I'm trying to poll for 1 second clips of audio (as fast as possible) from my computer's microphone (and ...
1
vote
0answers
50 views

DumpGet::bgcor error

resource = ResourceObject["MNIST"]; trainingData = ResourceData[resource, "TrainingData"]; testData = ResourceData[resource, "TestData"]; This is an example ...
0
votes
0answers
54 views

Neural Network and Enforce Positive Vector

I am trying to implement a neural network where I output a vector of 5 parameters each of which I know to be positive. I have code that works where I end up with an `"Output" -> 5.' However, after ...
1
vote
0answers
77 views

Unable to retrieve NetModel in 11.2

In v11.1, I can retrieve a trained model with net = NetModel["LeNet Trained on MNIST Data"] However, in v11.2, this returns with a ...
13
votes
1answer
615 views

AI reinforcement learning via asynchronous advantage actor critic?

It has been almost 2 years since a major breakthough in AI research made Reinforcement Learning computationally feasible on laptops even without use of GPU computing: https://arxiv.org/abs/1602.01783 ...
0
votes
0answers
113 views

Change Loss Function in NetTrain

For a similar problem, I am trying to modify the code here (https://www.wolfram.com/language/11/image-and-signal-processing/image-recognition-using-deep-learning.html?product=mathematica) so that the ...
2
votes
0answers
85 views
2
votes
0answers
284 views

What are the default parameters for ADAM optimizer?

ADAM Optimizer (used for optimizing the loss function for neural networks) consists of 3 free parameters: $\eta$, stepsize/learning rate $\beta_1$, forgetting factor for gradients $\beta_2$, ...
8
votes
1answer
415 views

NetTrain automatic settings

I'm trying to compare Mathematica's NetTrain with other algorithms, and I used Automatic settings as they were working quite ...
4
votes
1answer
347 views

Cropping in neural networks

The problem I am stuck with is in cropping tensors at certain parts of the network to obtain specific dimensions. I am trying to construct the U-net convolutional neural network. Almost all of the ...
10
votes
3answers
670 views

Approximation with radial basis functions

I want to approximate some functions with basisfunctions, which can be easy Fourier-transformed. So I got the idea to approximate my function with Gaussian normal-distribution curves. This led me to ...
2
votes
0answers
81 views

Specifying feature types for BayesianMinimization

I'd like to use Bayesian optimization over a pair of features, one nominal, one numerical. If I do something like this: ...
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* ...
3
votes
1answer
262 views

Machine learning classify function with audio and set of pictures

As I see from documentation, Classify function supports Audio and Pictures as input, video is not supported unfortunately :( Will it work if I try to use classify for mixed data input like ...
10
votes
3answers
751 views

Using Mathematica wlnet model in C++

Suppose if there is a trained net: SeedRandom[1234]; net = NetInitialize@NetChain[{5, 3}, "Input" -> 2]; It can predict image in mma: ...
13
votes
2answers
431 views

Simple example of NetGraph running in MXNet?

There is an great example of exporting a NetGraph (that was trained in Mathematica) into the MXNet's format. However, I think there's a bug or something is wrong with the answer, because once ...
2
votes
1answer
146 views

Can Predict return non-numerical values?

I just started working with the Mathematica machine learning package. When I use Predict, I can predict only numerical values like ...
2
votes
0answers
46 views

How to add sugar for NetEncoder?

I'm tired of the extra level of list in NetEncoder and would like to get rid of it. The obvious thing fails: ...
1
vote
0answers
147 views

How to train a network using out of core training when data have different length?

I posted How to use Mathematica to train a network Using out of core classification? some month ago. The network receive some fixed-length input and produce another fixed-length output,this is How to ...
6
votes
1answer
4k views

How to train Sequence-to-sequence autoencoder using LSTM?

According Keras blog,I find the Seq2Seq auto-encoder. But it didn't give any example only code. To build a LSTM-based autoencoder, first use a LSTM encoder to turn your input sequences into a ...
2
votes
1answer
122 views

Neural network giving different answers

I'm very new to machine learning and pretty new to Mathematica, trying to implement a simple neural network that acts as a "XOR" gate. Here's my code: ...
4
votes
1answer
278 views

Weighted Data within Classify and Predict (or NetTrain)

I posed this on Wolfram Community about a week ago and no one there seems to have a good solution, so I will try it here. (It may well be that this is an issue for Mathematica developers and that ...
4
votes
0answers
103 views

Transfer Learning: How to take certain layers from a pre-trained neural net, add it to a new net, and keep its variables fixed? [duplicate]

How can one copy specified layers from a pre-trained neural network and add them to another trained neural net? For instance, ...
1
vote
0answers
40 views

Dynamically adjusting BatchSize during training of NetChain

Is it possible to dynamically adjust BatchSize during NetTrain training session? For instance, can I create a schedule to adjust BatchSize based on the training round? -CJ
3
votes
1answer
203 views

How to reserve the Training Progress Panel after training

After the network train, the Training Progress Panel will disappear in MMA.But the panel always give a lot of information about the trained result. Such as this net ...