Podcast #128: We chat with Kent C Dodds about why he loves React and discuss what life was like in the dark days before Git. Listen now.

Questions tagged [neural-networks]

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

Filter by
Sorted by
Tagged with
5
votes
1answer
359 views

How to build a NetChain by the information of ClassifierFunction?

NetChain provides a method NetExtract. I want to see how standClassify = Classify[trainingData, Method -> "NeuralNetwork"] works,beacause it has a better ...
13
votes
1answer
1k views

How to visualize attention?

In the articles about sequence attention we can see images like this: Here we see that while translating from French to English, the network attends sequentially to each input state, but sometimes it ...
5
votes
1answer
195 views

Using a classification Neural Net and parameter to ClassifierMeasurements[]

I created and trained a simple neural net, which takes some inputs and produces a 3-class classification. Then I feed it to CM[] function with some test data, and... nothing. Haven't been successful ...
3
votes
1answer
100 views

Nesting NetGraph and accessing inner NetPorts

Can NetGraph be nested and how does once access the inner ports of such a nested network? The documentation does (to my knowledge) not specify this and there are no ...
2
votes
0answers
101 views

Neural Networks: Missing functions/data

Newcomer to both Mathematica and neural networks here, so please bear with me. I'm running Mathematica (11.0.1) on a school server (Ubuntu 14.04), accessing it via ssh. I'm trying to follow the ...
10
votes
1answer
928 views

How to change weights of a neural network

Is there a way to change the weights of a layer in a neural network, without reconstructing the whole network? For example, ...
7
votes
3answers
644 views

how to take ImageFeatures?

I want to know how to transform images to feature vector. There is a function FeatureExtractor.And it has some methods. ...
5
votes
1answer
224 views

How to write a RCNN (region-cnn)?

Has anyone end-to-end trained a single net that can find the location of objects in an image (with v11.1)? Here's an example of a region-cnn in action, and this is a good description of the approach.
3
votes
0answers
278 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. ...
7
votes
1answer
337 views

Implementing Resnet as a NetGraph?

Does anyone know of a Mathematica v11.1 implementation for any of the Resnets, e.g. a NetModel or WLNet for Resnet-1000? Loading the MXNet weights from the model zoo for both resnet or resnext doesn'...
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 ...
3
votes
1answer
399 views

Progress bar explanation NetTrain

I was wondering what the progress window that appears when I call NetTrain is trying to tell me. There are 7 values given and one graph: round batch inputs/second (...
4
votes
1answer
370 views

Extract training and test set performance from a neural net

I would like to extract a graph of the history of a neural net's performance, as it is trained. This is so I can compare it with the equivalent from Tensorflow (for some reason an equivalent network ...
5
votes
0answers
434 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 ...
5
votes
2answers
148 views

SoftmaxLayer Incompatible types

Trying to create U-Net similar to this paper from this GitHub project but keep getting "incompatible type" error on the final softmax layer. Any ideas for how to organize data to satisfy Softmax layer?...
1
vote
0answers
115 views

Multiple use of an identical layer in neural networks

I am trying to train a net on a time series. It gets a set of points (x,y) as input and should try to predict the first point after the series. Now I use those and the calculated point to predict the ...
3
votes
1answer
256 views

Custom NetEncoder for lower resolution image input in a pre-trained Inception network

I have come across this neat explanation on how to adjust a pre-trained Inception neural net to an arbitrary number of classes by truncating the top layers. However, my input data does not come in $...
45
votes
2answers
2k 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 ...
2
votes
1answer
472 views

CNN Nettrain problem

I 500 pictures of tables and chairs each (849x849) and want to train a convolutional neural net to classify new pictures accordingly. This is my code so far: ...
6
votes
1answer
2k views

Parsing a caffe prototxt file?

Caffe has its own visualization tools, for instance you and draw all the layers in a network easily like so: But I wanted to analyze a network structure myself in mathematica, so I started to write a ...
2
votes
0answers
135 views

Why not all properties in ClassifierMeasurements are available?

I'm doing an experiment of objects classification on dataset CIFAR-10 and I'm doing this using a neural network. The basic code of this experiment is come from the demo on Mathematica website and I ...
42
votes
3answers
6k views

How do you make a Neural Net?

In the new Mathematica release (v11), NeuralNetworks is one of the new main features. However, the documentation isn't that clear on what function should be used in ...
9
votes
1answer
159 views

What non-obvious functions work on neural network objects?

I've learned in a recent Virtual Conference that I can use Take to get a subnetwork from a neural network object, so e.g. ...
13
votes
1answer
2k views

How do I configure the input and output layers of a neural network?

I'm confused about how to set some of the basic properties of a neural network structure using Classify. I'm trying to set the basic properties of a simple neural ...
6
votes
1answer
385 views

Neural Networks: Modifiying NN structures?

From this nice answer one can import pretrained NN models and structures for state of art models. ...
17
votes
3answers
2k views

Neural Network for polynomial fit

I'm trying to build up a neural network with Mathematica 11.0, that should fit data which behaves like a polynom of third order. I thought that an NN with one or two hidden layers can fit any function,...
3
votes
1answer
238 views

Extrapolate data from Predict function

I'm trying to predict the next Close value in the S&P500 index using the following code: ...
25
votes
1answer
1k views

How to monitor the process of Neural Network Learning

Main Problem I'm exploring the neural network in v11 and I would like to monitor the training progress in my own way instead of Mathematica's default way. So my question is, how to do this ...
2
votes
1answer
172 views

NetTrain ClassifierFunction/NetChain Entropy

Obtain a trained network from NetTrain as net = NetTrain[net, dat]; which i believe returns a ClassifierFunction (although Head[net] returns NetChain). In ...
13
votes
1answer
1k views

Is there any decent deep learning library in Mathematica?

Deep Learning is the currently trending method in machine learning community. Some languages like python and matlab have some very convenient toolbox for deep learning. So is there any decent deep ...
8
votes
1answer
621 views

Which GPUs does NetTrain work with?

NetTrain's option TargetDevice -> "GPU" works for old macbooks that have GEForce GT 750m cards (like mine), but what about other nvidia cards? Does it (or will ...
2
votes
0answers
118 views

Are there any examples of wlnets?

I'm looking for some examples of the new neural network file format (.wlnet) introduced in v11. Has anyone made or found any available ones, to import and use?
11
votes
0answers
501 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 ...
7
votes
1answer
709 views

Use autoencoder for dimensionality reduction

I have been trying to follow this tutorial (https://www.wolfram.com/language/11/neural-networks/unsupervised-learning-with-autoencoders.html?product=mathematica) to train an autoencoder in Mathematica,...
3
votes
0answers
170 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/...
9
votes
1answer
255 views

How can I train a neural net to decide the 3rd digit of a number?

As a "toy problem" to explore the new neural net library, I wanted to train a neural net with: Input: 1 real number in the range [0, 1) Output: the nth digit (i.e. one of {0, 1, 2, 3, 4, 5, 6, 7, 8, ...
8
votes
2answers
627 views

Training data generator?

Python has generators which save memory, is there a technique for generating in memory examples for your training set "on the fly". For example purposes, I constructed here a regressor for blur: <...
7
votes
1answer
320 views

Memory leak in NetTrain?

Issue NetTrain seems to leak memory. Example We define a simple NetChain: ...
8
votes
1answer
382 views

Neural net example not working

Bug introduced in 11.0.0 and fixed via paclet update The Wolfram Mathematica site provides this example. I have copied and pasted into a notebook. The resource is reached and correctly sampled. ...
10
votes
1answer
126 views

Bug when importing Neural Nets from .m files in a fresh kernel

Bug introduced in 11.0.0 and fixed in 11.0.1 Importing Neural Nets from .m files seems to destroy the neural net. ...
9
votes
1answer
590 views

Can someone explain how the dilation in the ConvolutionalLayer works?

ConvolutionalLayer has a few optional parameters. "Dilation" is one I'm having trouble understanding how it works and the documentation is terse. Can anyone give some explanation? References: https:...
7
votes
2answers
516 views

Staged training of Neural Networks

From what the documentation says about NetTrain and NetInitialize and what the progress indicator shows when reevaluating ...
5
votes
1answer
249 views

Updated: Correct Formatting of Dataset (labeled columns and rows) for Predict v NetTrain?

Problem I can not seem to figure out the correct way of formatting Dataset to be used with predict. I am providing Mathematica's example, which works fine. I also am including an abitrary "dataset" ...
7
votes
1answer
443 views

NetEncoders vs MXNet preprocessing

According to this great answer, the MXNet framework powers Mathematica's new neural net functions. So I wanted to check and make sure the results agree for a pretrained network (available here: https:/...
11
votes
1answer
268 views

How can I train a neural net with multiple categorical inputs?

I think I understand how to create a neural net that has multiple categorical inputs, but I don't seem to be able to invoke NetTrain successfully on it. As a ...
30
votes
2answers
3k views

Using a Convolutional Neural Network for time series classification

In the recent new in Mathematica 11 webinar one user asked during the Q&A session wether the current implementation of neural networks in Mathematica 11 could be used for processing time series. ...
11
votes
1answer
861 views

A comprehensive list of all correct input formats for [[experimental]] Neural Net functions?

Question: correct formats for Mathematica's NetTrain function Explanation of the problem Background So Mathematica 11 was released earlier this month, and while there are many improvements and they ...
34
votes
1answer
3k views

RNN in Mathematica?

Recurrent neural network is an important part of machine learning and its improved version: LSTM network is widely applied, but Mathematica seemingly is in lack of these two features and in my opinion,...
3
votes
0answers
76 views

Undo automatic update [closed]

I was working with Predict function (with a neural network and today, and when I executed the same notebook I have been working for some time, Machine Learning package was automatically updated (it ...
0
votes
1answer
89 views

What's going wrong with this button! [duplicate]

I'm implementing an Adaline algorithm where all inputs are 1x5526 and the output is a number from 1 to 10. I have this two functions defined and worked outside the ...