Questions tagged [machine-learning]
Questions about machine learning functionality of Mathematica, for instance involving, but not restricted to, Predict, Classify, FindClusters and the various regression functions.
688 questions
7
votes
1
answer
206
views
Feature Extractor for Molecules
Running FeatureSpacePlot[mols] gives me an interesting plot and I would like to understand the method.
Does anyone know or can point me to a reference page on how ...
- 931
-1
votes
1
answer
85
views
k-fold cross-validation
I have my dataset as a Tabular object and I would like to perform a 5-fold cross-validation to evaluate Classify. What is the ...
- 159
1
vote
0
answers
65
views
Numerical optimization on PredictorFunction fail with region specification but not constraint specification
Problem:. Numerical optimization on learned PredictorFunction do not seem to behave the same for constraint and region specifications, and the latter fail to ...
- 3,683
1
vote
0
answers
53
views
Additional stopping criterion for ActivePrediction?
ActivePrediction ---the active learning version of Predict---allows for one to set the MaxIterations options to determine a maximum number of samples requested. Are ...
- 3,683
0
votes
0
answers
46
views
Unable to download training dataset, getting CloudObjecy error?
I'm doing the WolframU ML course and trying to download the training dataset for FashionMNIST, however am consistently getting this error (which also only seems to then download 2 samples):
...
0
votes
0
answers
83
views
How to tailor the input of a predefined network to match my own data?
I'd like to use the ResNet V2 on my own data, but my data is not image. Let's say my data is a list of numbers or a time sequence. Therefore, I decided to revise the ResNet V2 a little bit.
...
3
votes
2
answers
338
views
2
votes
0
answers
133
views
n-Dimensional centroid for Universal optimization algorithms
Background
Over the course of his career, Thomas Cover developed the concept of "natural optimization", with which he addressed problems where an optimal strategy emerges naturally through a ...
- 14.7k
0
votes
1
answer
216
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
...
- 524
1
vote
0
answers
63
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)
...
- 524
0
votes
0
answers
94
views
Combination of decoder and encoder for VAE interpolation
To get VAE interpolation I need decoder and encoder to be combined. Can you make a suggestion?
...
- 11
0
votes
1
answer
116
views
Scheduled Updating of LossFunction Scaling in NetTrain
I'm looking for a way to externally manipulate (hyper)parameters of a network during NetTrain training, as a function of the training progress. Specifically, I want ...
- 347
0
votes
1
answer
105
views
Use of ports on basic machine learning regression
I have this simple code to do a regression on a list of points very close to a parabole. It is purely anecdotal that I happen to know the exact underlying trend, the idea is just to have simple/nice ...
- 524
2
votes
0
answers
61
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 ...
- 3,880
0
votes
1
answer
131
views
Neural network that augments the input with constants
Suppose we have a simple neural network as follows:
...
- 487