All Questions
Tagged with machine-learning or machine-learning
234 questions with no upvoted or accepted answers
3
votes
0
answers
592
views
Pattern recognition
I am trying to have Mathematica come up with a simplified version of a real pattern. For the moment I'm trying with handwritten digits, but eventually I want to apply it to more complex photographs.
...
- 2,470
3
votes
0
answers
85
views
What ratio of example per class gives best results and least overfitting?
For an n-class classifier or predictor, how many positive (or negative?) examples of each of the n classes should I put into my training and testing sets for the best results?
I anticipate that ...
- 31.8k
3
votes
0
answers
154
views
How does Mathematica automatically choose which classifier method to use?
I'm interested in what heuristics are used in Classify's choice of method.
- 31.8k
2
votes
0
answers
54
views
Publishing image classifier as a website or to the cloud
I have made an image classifier by importing images and training my neural network, and I would like to share this classifier with my colleagues that don't have access to Mathematica.
However, if I ...
2
votes
0
answers
145
views
Machine learning for symbolic mathematics
I came across a meaningful article about the use of machine learning (in particular, with Mathematica) to solve ODEs and find undefined integrals. Are there any other works, especially done with ...
- 29.1k
2
votes
0
answers
61
views
Unable to Replicate an ANN Using the Output from Predict Function
I’m working on constructing an ANN. I first used the Predict function with the method “Neural Network” to determine the structure according to my data.
This is the given output of the structure:
...
- 21
2
votes
0
answers
47
views
FeatureExtraction for TimeSeries giving errors
I'm trying to replicate this example using FeatureExtraction for TimeSeries. However, it's giving errors.
Here's the code I've run:
...
- 193
2
votes
1
answer
175
views
CrossValidate for image classification with NetTrain
I am trying to set up transfer learning using instructions from this repository page on EfficientNet. I am able to perform a stand-alone training and testing using the instructions on that page. The ...
- 739
2
votes
0
answers
57
views
Preprocessing data\[Ellipsis]. or Preprocessing data..... error in ParallelTable in Mathematica
I am working on Machine Learning. My purpose in the code is to repeat calculation a few times and average the results. While using Table command, following message pops up for ClassifiersMeasurements ...
- 557
2
votes
0
answers
32
views
Does NetChain have a "Distribution" property like PredictorFunction?
PredictorFunction has an incredibly useful "Distribution" property. In the past, this has helped me filter out bad predictions, like this:
...
2
votes
0
answers
160
views
Simulated Cartpole Example in Mathematica
I am interested in modifying the code underlying the reinforcement learning example SimulatedCartpole in Mathematica 12.
This example is still listed as Experimental. The help function indicates that ...
- 131
2
votes
0
answers
137
views
How to specify custom Loss function for Predict
How can I use Predict[Xs->Ys, Method->"NeuralNetwork"] to predict 90%-quantile (instead of mean value)?
Utility Function does not work well for this case, because
it assumes ...
- 121
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
78
views
What are all the machine learning methods that can be used for Predict?
When I'm writing code for the Predict function, it allows me to choose what method I want to use. There are 7 options available from the drop-down after I type in <...
- 539
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
2
votes
0
answers
33
views
Retrain an existing ClassifierFunction with new data
Classify[] and Predict[] generate nice ClassifierFunnction, but it is not clear to me whether these can be retrained on new data, without the data originally used for training.
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
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
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
2
votes
0
answers
123
views
LearnDistribution Vs FindDistribution?
How would you explain the difference between the new LearnDistribution function and the FindDistribution function? or perhaps the overall ML vs Find framework.
I would think for a sample size of 1000 ...
- 71
2
votes
0
answers
270
views
Hessian of a loss function for a neural netwrok
Is a way to calculate the Hessian of the loss function in Mathematica. It's easy to define a loss function for neural nets but I couldn't figure out how to calculate the Hessian(more precisely I ...
- 727
2
votes
0
answers
111
views
Concise way to set input directory
Got this Mathematica ResNet- 50 Code online and has been trying to make run it using the same data set but it seems my directories to the dataset were not correct, keep getting this error:
...
2
votes
0
answers
90
views
Confusing errors using predict to map between matrices
I'm messing around with the new features involving machine learning in Mathematica 11, and one easy thing to try is to make a machine learn the matrix exponential function. The first silly idea I had ...
- 667
2
votes
0
answers
53
views
Calculate the precision@k in Classify
I am interested to measure a precision@k. The Classify function provides a build in an option for that or an elegant approach to calculate this without the need to ...
- 2,019
2
votes
0
answers
161
views
How to use UnitVectorLayer in a NetChain?
How can I create a NetChain with UnitVectorLayer inside?
In this way I receive this error:
...
- 393
2
votes
0
answers
161
views
Why is the output of the Embedding layer so non-linear?
I have 2 nets, i.e. net1 (i.e. LinearLayer) and net2 (i.e. ...
- 3,509
2
votes
0
answers
112
views
Does Mathematica auto update something causes error load old-version model?
I've trained a NN model by NetTrain with Mathematica 11.3.0, and I can load the model correctly to predict.
My model is saved by .mx format.
After few months, I cann't load the model correctly.
...
- 8,649
2
votes
0
answers
71
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
...
- 3,509
2
votes
0
answers
95
views
Significant performance differences with "Predict" function between v10 and v11
So I am very new to ML. I tried running this code in Mathematica 10.4.1.0
...
- 21
2
votes
0
answers
107
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:
...
- 1,002
2
votes
0
answers
113
views
ClusterClassify and FeatureTypes
I have a dataset that I want to classify in clusters. All values are numbers.
For some variables, the values can represent a real measure (a distance, a weight...) but for some other variables, the ...
- 347
2
votes
0
answers
1k
views
Stochastic Gradient Descent with constraints
Let's say we have a convex objective function $f(\textbf{x})$, with $\textbf{x}\in R^n$ which we want to minimise under a set of constraints. The problem is that calculating $f$ exactly is not ...
- 841
2
votes
0
answers
90
views
Is there a way to monitor progress of Classify?
NetTrain provides great feedback while doing gradient decent or any other training method.
Is there a similar way to monitor training details with a call to ...
- 31.8k
2
votes
0
answers
101
views
Why my symbols been cleared?
I have about 60000 data to train.
After minutes of calculation,all symbols are cleared.
Is it a Bug?
I have 8G memories ,but it's not enough.My cpu is i5-4590.
Here are my codes:
...
- 449
2
votes
0
answers
166
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 ...
- 166
2
votes
0
answers
250
views
Binary Image Classification using convolutional layer
I have a sample of images of chairs and tables and I want to use a neural network using convolutional layer and gpu-acceleration for training. This is what I have so far - how do I train the network?
...
- 247
2
votes
0
answers
958
views
Max iterations in K-means clustering algorithm
I want to use k-means for clustering. I have used the ClusteringComponents function but I said how can I control the max-iteration for k-means ?
- 2,046
2
votes
0
answers
1k
views
How do I obtain the Fisher information matrix from a data set?
My apologies in so much as this is probably in large part a problem of me not being aware of the necessary mathematics but since this should be a common issue in machine learning and Mathematica now ...
- 111
1
vote
1
answer
84
views
Training a neural network on two dataset simultaneously
I have my neural network model and want to train it at the same time on 2 datasets that share the same structure. What I have done so far does not work.
This is my code
...
- 516
1
vote
0
answers
29
views
Is this a reasonable way to transform simple MSE loss function to weighted MSE for neural networks?
The idea is tested on a dataset with a clear outlier (see picture below)
...
- 516
1
vote
0
answers
25
views
How to evaluate text-to-speech models in WL
There are a many solid options for text-to-speech (TTS) now in SpeechSythesize and from API providers in general. How might I use Mathematica to compare the quality ...
- 3,830
1
vote
0
answers
38
views
TensorProduct in a FunctionLayer cannot compile correctly
My network can output an array of 6x512x512 size at the end, now I want to multiply an array of length 3 for each of these 6 channels to get the color of the different channels, I am using the ...
- 83
1
vote
0
answers
96
views
Why does ridiculous error information appear in Classify with Method GradientBoostedTrees?
The data could be classified correctly by method like LogisticRegression, NearestNeigbors.
The dataset is quiet simple, ...
- 8,649
1
vote
0
answers
96
views
What is that neural network?
I am teaching my comp to add naturals by creating a neural network:
...
- 29.1k
1
vote
0
answers
147
views
Mathematica, ML and TensorFlow
I am currently studying a specialization on Coursera in Machine Learning and am investigating various tools to help me out with the maths and with visualisations and so on.
Although I have many ...
- 111
1
vote
0
answers
104
views
Training stuck problem about SVM in Classify
fashion MNIST dataset
You can download the FasionMNIST and unzip the data, you'll see that train-images-idx3-ubyte.
You may also use official ...
- 8,649
1
vote
0
answers
43
views
Why Spectral Method and GaussianMixture in FindClusters and ClusteringComponents can't set the number of Clusters?
There is an official example, that we can set clusters number.
However, when I set the number to run the example, funny thing happens.
The same problem in ...
- 8,649
1
vote
0
answers
33
views
Differentiating matrix function in `Table` from
I am trying to get an analytical expression for derivaives of an algorithm explained here.
I usually use automatic diff. a lot, but since this part of function will not change, I thought to implement ...
- 111
1
vote
0
answers
62
views
How to measure a LearnedDistribution?
I would like to measure the qualities of a LearnedDistribution in general and with regard to test sets. The docs say that it takes an option ValidationSet, but ...
- 3,830
1
vote
0
answers
51
views
Is it possible to add new concept to ImageContents
I was hoping to use ImageContents to locate some specific objects in a series of images with a bounding box. However, ...
- 4,778