All Questions
Tagged with machine-learning neural-networks
300 questions
3
votes
0
answers
56
views
Training a neural network with post-processed data [closed]
I want to fit a large number of functions over a vector space with a neural network. I have a particular architecture in mind, which is naturally broken into two parts: the first part consists of ...
- 667
6
votes
0
answers
315
views
5
votes
1
answer
515
views
Loss function with regularization
The ML framework has a limited set of loss functions available. How can I extend this by creating my own custom ones?
For example, for L2-regularized training, Mathematica recommends
...
- 727
3
votes
0
answers
174
views
Classify/NetTrain run indefinitely without output when using GPU
I am experimenting with Mathematica's Classify/NetTrain functions for the first time.
When I don't set a TargetDevice option, Mathematica defaults to the CPU and everything works as expected.
When I ...
- 131
4
votes
1
answer
1k
views
Complex numbers in neural networks
I am trying to construct a neural network which fits a collection of functions from (complex-valued) vectors to complex numbers. After constructing a suitable network, I was surprised to see that ...
- 667
2
votes
1
answer
199
views
How to build an RNN with input as character but output a sequence of tokens?
Let’s assume I have “abbcab”-> {“Apple”,”Banana”}, “Bibb”-> {“Carrot”} so the output is a sequence of various length, but I can pad it to be the same length. My problem, how do I create a ...
- 21
2
votes
1
answer
71
views
What's the difference between train and test evaluation modes of a BatchNormalizationLayer?
After creating a BatchNormalizationLayer:
batchnorm = NetInitialize@BatchNormalizationLayer["Input" -> 3]
We can evaluate it in "Test" or &...
- 625
1
vote
1
answer
156
views
How is the loss computed from the batch and round?
This is cross-posted from the forum.
I am trying to just reproduce the loss computed during training a very simple network. In this case the loss is just the standard L2 loss function.
Start with some ...
- 625
2
votes
1
answer
188
views
Copying Weights using NetTrain in Mathematica
I would like to implement the PPO algorithm - Reinforcement Learning - in Mathematica. And for that, I need to be able to copy network weights from say subnetwork NN1 to subnetwork NN2 as an update ...
- 21
3
votes
1
answer
114
views
Can NetNestOperator take a non pre-defined number of iterations?
I'd like to Nest a particular NetChain inside a larger NetGraph for a random number of ...
- 4,415
2
votes
0
answers
30
views
Classify command option question
I'm using Classify to predict who is going to win a battle based on their strength. The input is something like {{"Name 1", Strength1},{"Name 2", Strength2},{"Name 3", ...
2
votes
0
answers
108
views
Questions on NetMapOperator, NetNestOperator, NetFoldOperator [closed]
I've been playing around with the Higher-Order Network Construction functionality such as NetMapOperator, NetNestOperator, and <...
- 4,415
11
votes
0
answers
235
views
Tutorial example NetTrain fails miserably with a GPU
I have been experimenting with GPU NetTrain on AWS now when Mma 12.2 supports remote batch jobs (I don't have an Nvidia GPU to try these things out otherwise). In ...
- 19.1k
1
vote
1
answer
124
views
Constructing Net problem
so I'm trying build a simple net that will help me find the winner in a competition. I would like to use as input "Name", "FA" and "Force", and obtain "Winner" ...
3
votes
2
answers
350
views
how to implement training for UNET implementation on Wolfram Neural Net Repository?
My question is with reference to the U-NET implementation present on the Wolfram Neural Net Repository
The construction notebook present on the page (link: http://...
- 9,060
15
votes
1
answer
533
views
Minibatch Standard Deviation Layer
I'm reworking some of the GANs I originally made in TensorFlow2 to see if I can improve performance in Mathematica, and have been stuck on how to create a custom Minibatch Standard Deviation Layer. I'...
- 1,256
5
votes
0
answers
158
views
How to train each layer in a Neural Network so they optimize different loss functions in an adversarial network?
Example NetGraph to illustrate the idea (Input is an online signal with a value between -1 and 1, Noise is Gaussian Centered at 0 and standard deviation 0.1, EvilNet is constrained to output a value ...
- 526
2
votes
1
answer
102
views
Want neural net example of rules {vector->string}
I am using data samples from a multispectral color sensor for color classification as an exercise in beginning to learn about neural networks.
I have succeeded with ...
- 23
2
votes
1
answer
203
views
Help with creating the NetChain
I'm trying to train a network to take 3 integers and give an output = Max/Min. For example {10, 20, 30} -> 3. But I cannot get the setup correctly. I must be missing something.
...
2
votes
0
answers
119
views
Create New Type of Layer For Neural Network
I'm doing some work exploring modelling neural networks in which each neuron could represent a different type of physical system. What I want to do is, I think, quite different to what an ordinary ...
- 360
6
votes
1
answer
1k
views
Save neural network after training
I've written quite a few projects that involve training a neural network through the Classify and Predict functions, but every ...
- 539
0
votes
0
answers
132
views
Neural network symbolic inputs and weights
If I create a neural network like, for example, so:
...
- 3,167
0
votes
0
answers
126
views
Interpolated Hyperbolic tangent as a layer of a neural network
It is necessary to specify piecewise linear interpolation of the hyperbolic tangent. And substitute this function as a layer of a neural network. I tried a lot of things, please suggest your options.)
...
- 11
0
votes
0
answers
94
views
Network training error InvalidJSON
I want to insert piecewise linear interpolation of the hyperbolic tangent into the neural network. An error occurs at the stage of training the network.
trainingData:
...
- 11
5
votes
0
answers
241
views
Seq2Seq RNN with an AttentionLayer
In many Sequence to Sequence machine learning tasks, an Attention Mechanism is incorporated.
Before Transformer Networks, introduced in the paper: Attention Is All You Need, mainly RNNs were used to ...
- 428
5
votes
1
answer
440
views
How to paraphrase text?
I'm looking to train or use pre-trained models in order to re-phrase text. Are there any natural language models in the Wolfram Neural Repository (or elsewhere) that can be used to paraphrase text?
...
- 3,820
4
votes
1
answer
5k
views
GPU support on latest MacBook Pro, especially for deep learning
I'm thinking about getting some new top of the line computer hardware, specifically a MacBook Pro from Apple. These have AMD Radeon Pro 5500M GPUs, which while a bit slower than something like an ...
- 197
9
votes
1
answer
311
views
How to implement BlazeFace?
BlazeFace is a lightweight and well-performing face detector tailored for mobile GPU inference. It runs at a speed of 200-1000+ FPS on flagship devices. How to implement BlazeFace in Mathematica?
- 9,621
9
votes
2
answers
327
views
Can I use Mathematica to generate candle scents?
I found this blog (which is highly entertaining). It has an interesting post where the author uses the GPT-2 neuro-network with candle scent training data to generate new candle scents. The AI comes ...
- 4,778
4
votes
0
answers
133
views
Neural network for a simple game?
I'm taking a class that is based on the Mathematica coding language, and we must do a 6-week final project. I am considering coding a neural network for a simple game like 2048, pacman, snake, etc. ...
4
votes
1
answer
184
views
Adding Noise in Neural Net via ElementwiseLayer
I am trying to add noise to a neural net to train a denoising autoencoder. I don't want to pre-calculate the noisy data. Rather, I'd like the noise be applied via a function using the ElementwiseLayer....
- 43
1
vote
0
answers
57
views
Training with GPU and tuning parameters with ParallelTable
We intend to train a neural network. It has a hyperparameter, such as the learning rate. We want to compare the training results of different hyperparameters. Our computer has two multi-core CPUs and ...
- 11
2
votes
0
answers
76
views
Fuzzy Logic and Neural Networks
Is anyone working on building a Fuzzy Logic module that can be used for the output of Neural Networks?
Thank You
Michel
- 191
6
votes
0
answers
186
views
How can I prevent errors with ReplicateLayer[]?
I am trying to build a NetGraph[] that takes input of the form {{0.6},{0.6},...,{0.8},{0.8}} and multiplies the last sequence ...
- 1,447
2
votes
0
answers
417
views
is the code of this reinforcement learning example correct?
I am trying to learn reinforcement learning from an article on Wolfram.com, and after several days I still cannot quite get everything right. Now I wonder about the correctness of a piece of code ...
- 131
2
votes
1
answer
111
views
How can I use ThreadingLayer to perform operations with layers of different dimmensions?
Is there a way that I can achieve subtraction between a scalar and a vector within NetGraph[], similar to what happens when I perform ...
- 1,447
4
votes
1
answer
209
views
Controlling learning rate decay or cyclic learning rate in Mathematica's neural nets
I am using Mathematica's NetTrain[] function for training neural nets. There is a way to set the learning rate (LearningRate and ...
- 131
14
votes
3
answers
605
views
Importing a grid of numbers from an image (sudoku like)
Can anyone see a way to import a grid of numbers from
http://www.mit.edu/~puzzle/2019/puzzle/lantern_festival.html
into Mathematica? TextRecognize doesn't seem ...
- 6,697
3
votes
1
answer
654
views
Rounding the output Vector of a Neural Network layer to prepare it for the next layer
I am attempting to Round up the output Vector of a Neural Network layer to prepare it for the next layer
Ex. Layer output {.1.,2.2,3.3} and I need it to be a Vector of Integers for the next layer.
I ...
- 191
5
votes
0
answers
292
views
Image-based reinforcement learning with neural networks
After seeing that "OpenAIGym" is not exactly supported on Windows and playing around with https://www.wolfram.com/language/12/neural-network-framework/train-an-...
- 406
1
vote
0
answers
117
views
0
votes
1
answer
114
views
Transform function {a,b} ->{x,y} ; how to?
I have a 2D list of values that I want to transform/calibrate to another 2D list. I thought of using a predict function but I couldn’t get it to output 2 values.
—...
2
votes
1
answer
155
views
Mathematica classify NeuralNetwork default parameters
We have trained a Neural Network on Mathemetica classify with one hidden layer and received good classification results. We would like to know the default parameters beside it has one hidden layer? ...
- 21
2
votes
0
answers
246
views
How to train custom objects using YOLO in Mathematica?
I want to train few custom object using YOLO V2 architecture but not sure how to do this. I know that with the NetTake and NetReplace, this is achievable. Can someone point out me in the right ...
- 21
3
votes
0
answers
64
views
Net layer that replicates last element
I am trying to design a neural network layer that takes in an array of dimensions n x 100, and produces an array of dimensions ...
- 3,674
2
votes
1
answer
356
views
Using a neural net to make predictions
I want to use a neural net to give predictions, but I am not sure where to start. I do know that I don't want to use the high-level Predict function.
So what I ...
- 453
2
votes
1
answer
100
views
Output of the trained neural network for a set of inputs
Sorry if this was too trivial but I want to get the output of the neural network I trained for the specific inputs that I feed. The notation I often saw was of TrainedNet[inp] kind. But when I use ...
- 75
2
votes
1
answer
74
views
Chaining NetGraphs
I have two NetGraphs, each with 3 different input ports ("Input","Random1","Random2"), the first with 2 outputs ("Output" and "Loss") and the second with one output "Final_Out". All I want to do is "...
- 3,674
5
votes
1
answer
1k
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 ...
- 3,820
6
votes
0
answers
118
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 ...
- 61