The Stack Overflow podcast is back! Listen to an interview with our new CEO.

Questions tagged [neural-networks]

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

Filter by
Sorted by
Tagged with
86
votes
1answer
11k views

Crack CAPTCHA using deep learning

Deep convolutional neural networks are very good at computer vision related tasks. Optical Character Recognition (OCR) is one important branch of computer vision. In fact, the convolution neural ...
70
votes
6answers
4k views

Q&A Mathematica v.11 Neural Networks: A comprehensive look at Layers, Net Functions, and pioneering into this [[experimental]] code

Motivation As Mathematica v.11 was released earlier this month with a host of new [[experimental]] functions and a limited number of examples on curated data that ...
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, ...
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 ...
44
votes
2answers
6k views

Object detection and localization using neural network

Four important computer vision tasks are classification, localization, object detection and instance segmentation (image taken from cs224d course): These four tasks are all built on top of the deep ...
44
votes
4answers
3k views

Generative Adversarial Network

Generative adversarial networks (GAN) is regarded as one of "the most interesting idea in the last ten years in machine learning" by Yann LeCun. It can be used to generate photo-realistic images that ...
42
votes
3answers
5k 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 ...
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,...
33
votes
1answer
1k views

How can I export my learned ClassiferFunction[] and PredictorFunction[]s?

Mathematica 10 provides beautiful high-level machine learning functionality. Sadly, the learned functions once created are rather opaque objects. I need to use them in other projects, so here is my ...
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. ...
29
votes
3answers
852 views

How to make a custom NN layer in Mathematica?

Is there a way to create our own custom layers for Neural Networks in Mathematica ? I suspect it should be possible, any pointers or directions on how to go about it? I am interested in ...
28
votes
4answers
1k views

Neural Networks: Does Mathematica (v11) experimental code support state-of-art Models?

Mathematica made a big step implementing Neural Networks. I checked some examples for deep learning (ChainNet), also the related link. I see that model structures such as LaNet can be developed. ...
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 ...
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 ...
20
votes
1answer
1k views

How to import a Tensorflow model?

I've trained a network in Tensorflow and have the checkpoint files, I'd like to if anyone has written a parser or importer to pull the evaluation graph and/or weights into Mathematica?
20
votes
0answers
292 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
5answers
2k views

Recurrent neural network in 11.1 explicit examples?

I heard that RNN was implemented in Mathematica as of 11.1. Trying to search online, I find some general information about neural networks in Mathematica, or a list of related functions. My trouble is ...
19
votes
0answers
612 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 ...
18
votes
4answers
910 views

How to use Mathematica to train a network Using out of core classification?

I see there is doc about how to train a network Using out of core image classification and this question.But the object is only image. I want to use a binary file as data(Sequence to Sequence case),...
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,...
17
votes
1answer
2k views

Reference request for neural network programming in Mathematica

I'm looking for a good reference/book on programming neural networks in mathematica. I've been working through Freeman's "Simulating Neural Networks with Mathematica," but it is from 1994 so is quite ...
16
votes
1answer
1k views

How to implement a stateful RNN?

If the model is stateless, the cell states are reset at each example. With the stateful model, all the states are propagated to the next example. Stateful RNNs can learn the long sequences. For ...
15
votes
2answers
954 views

How can I add noise to a neural network input?

A common "trick" in neural network training is to train an autoencoder using a "degraded" sample as input and the original sample as target output. The layer type ...
15
votes
1answer
410 views

Training Neural Networks on Cloud GPUs (Wolfram Cloud / AWS / Paperspace /etc)

I have spent a lot of time lately training neural networks. However, my poor laptop has only an AMD GPU, so I am stuck training these networks on the CPU. That means I get to train networks over ...
14
votes
1answer
269 views

WLNet format incompatible between version 11.0 and 11.1

It seems that there are some behavior changes of neural network layers from version 11.0 to 11.1 that leads to the incompatibility of WLNet format. Consider this example: Network exported in 11.0 <...
13
votes
4answers
605 views

Neural network illustrations

(Since this post was met with a certain reluctance to be given answers, a version of it is also posted in Community.) Please share neural networks diagrams you have made in Mathematica / WL. Here is ...
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 ...
13
votes
1answer
1k 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 ...
13
votes
2answers
2k views

How to train a convolutional neural net on images?

The functions Predict[] and Classify[] both have the option Method -> "NeuralNetwork", ...
13
votes
2answers
546 views

How to implement a triplet network with NetSharedArray?

In v11.3, NetSharedArray[] and NetInsertSharedArray[] give us a mechanism of sharing weights and biases across neural networks, ...
13
votes
1answer
606 views

Neural machine translation model using deep learning

In Mathematica version 11.1, SequenceAttentionLayer is introduced to model attentions in the recurrent neural network. It has been shown that attention mechanism ...
13
votes
1answer
603 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 ...
13
votes
1answer
995 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 ...
13
votes
2answers
428 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 ...
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 ...
12
votes
3answers
336 views

Convert List of Associations into Association of Lists

For neural networks mathematica likes 2 ways to structure training sets: ...
12
votes
2answers
1k views

How to implement neural style transfer?

In the paper A Neural Algorithm of Artistic Style, Leon A. Gatys et all. describe a process of extracting the content and style vectors from an image separately. They use this technique to generate ...
12
votes
1answer
684 views

Counting parameters in a neural network

Is there a feature to automatically count parameters in a model? In Keras one can use layer.count_params() to get a count of parameters in a layer or ...
12
votes
2answers
633 views

Implementing a Neural Network

TLDR: I am implementing a neural net in Mathematica and need help with back propagation. This is purely for the joy of implementing a neural network with a functional programming language. If someone ...
12
votes
1answer
890 views

Configuring GPU for NetTrain

I currently have access to a system with two GPUs: GeForce GTX 1080 and Tesla K40c I would like to use this machine for training neural networks in Mathematica. When using the option ...
12
votes
2answers
441 views

How to define a PixelShuffle Layer?

PixelShuffleLayer come from Real-Time_Single_Image. Firstly, a $C\times H\times W$ image, after a convolution, now $f^2\cdot C \times H\times W$, then sub-pix, finally get a $ C \times fH\times fW$ ...
12
votes
1answer
341 views

Using PredictorMeasurements with a neural net?

PredictorMeasurements doesn't work with NetGraph, here's an example: ...
12
votes
1answer
719 views

Same neural network gives different results

I was playing with the neural network in Mathematica and found that the same neural network gives different classification results to the same image, which is very strange. Consider classifying this ...
12
votes
1answer
367 views

How to determine which Layers should be used in my NetChain?

I have a answer in this post which is based on neural network,but I have to say that reault is too bad and have no practicability.I think the reason is that selection of network layers.So I give some ...
12
votes
0answers
445 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 ...
12
votes
0answers
904 views

Neural network playground [closed]

I came across this Neural Net Playground demonstration based on Google's Tensorflow package. It visualizes the data processing inside a neural network and allows you to tweak parameters and ...
11
votes
1answer
416 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 ...
11
votes
2answers
683 views

Inspecting intermediate values in a neural network

Basically one creates a NetChain of several layers, trains it and by evaluating model[testdata], the prediction can be obtained. ...
11
votes
2answers
258 views

Export BatchNormalizationLayer as MXNet

Bug introduced in 11.2 and remains in 12.0.0 I just tried to import a net from mathemtica into pythons using MXNet. It works fine with the following manual. However, as soon as I try to add a ...
11
votes
1answer
266 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 ...