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.

159 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
27
votes
0answers
1k views

Handwriting recognition with Mathematica

I am trying to teach Mathematica to read my handwriting. Since I don't want to ruin my reputation by showing my own handwriting, I am going to use a font called blackjack. Lets say this is a ...
21
votes
0answers
696 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 ...
20
votes
0answers
386 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
0answers
176 views

Inefficient memory storage for Dataset

Why Dataset doesn't serialize its contents, isn't it the whole point? I expect it to behave similar to python's pandas.DataFrame,...
14
votes
0answers
508 views

How to plug holes in an Image (with partial convolutions)?

NVIDIA recently published a new way to reconstruct images with holes. They use a new type of convolutional layer which is described in the paper Image Inpainting for Irregular Holes Using Partial ...
9
votes
0answers
219 views

How to extract tree parameters from RandomForest?

I want to extract the parameters of a decision tree from the object estimated by Classify[]. It seems that parameters of the estimated Classifier are available in the "Models" property. It is ...
9
votes
0answers
208 views

What are the time and space complexities of Classify/Predict?

Does anyone have knowledge of the O(n) time & space complexities for various model types supported by Classify[] and ...
8
votes
0answers
114 views

Slow down training many neural networks (Bug?)

I am working on something in which I need to train a neural network many times with slightly different training data. I noticed that after many training runs the input rate had dropped significantly. ...
8
votes
0answers
343 views

Use of new machine learning capability for search problems (reinforcement learning)

I work with search algorithms, often of an adversarial nature, and want to understand how to apply Mathematica's machine learning capabilities, especially those new in version 11, to this type of ...
7
votes
0answers
370 views

How to train a bounding box detection model?

Apparently, this still isn't possible in v12? I'd like to add a new class to one of the standard object detection architectures. Consider the YOLO v2 detector from the Neural Net Repo. ...
7
votes
0answers
507 views

Train your own CycleGAN style translator

I have a set of images (a few hundred) that represent a certain style and I would like to train an unpaired image to image translator with CycleGAN. I'm looking for a tutorial on how one would do ...
6
votes
0answers
73 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 ...
6
votes
0answers
145 views

Export ImageCases to Python?

I’d like a tutorial on how to export a bounding box detector network to mxnet, (for bonus points: convert to Tensorflow), and then get it running correctly in python! Some related questions exist for ...
6
votes
0answers
257 views

How “good” is the new Classify and how does it choose its method

I recently read the blog regarding data-science Wolfram Blog and then checked the quality of the new Classify. I have a bunch of slides that I show to my students ...
6
votes
0answers
114 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 ...
6
votes
0answers
135 views

Create ClassifierFunction

Is there a way to create my own ClassifierFunction? I would like to combine predictions from multiple independent classifiers into a single ensemble ClassifierFunction and be able to use things like ...
5
votes
0answers
130 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 ...
5
votes
0answers
88 views

Recognising people from photos

I have a large number (probably 10000) of personal photos taken over the last few years, a good proportion of which contain family members. I'd like to put together a photo book of one family member,...
5
votes
0answers
99 views

Reverse Engineering of MMA `Classify[]` Output?

Update: as @AntonAntoniv rightly noticed in his comment the case of DecisionTree is already discussed. Now it would be great to also have an equivalent answer for LogisticRegression. MMA is really ...
5
votes
0answers
75 views

Can I extract symbolic expression of neural network loss function?

Once we create a neural network with NetChain in Mathematica, can we extract the loss function in the symbolic form for Mathematica to play with symbolic manipulations using Mathematica's built-in ...
5
votes
0answers
105 views

How to extend ImageCases?

I was very excited to see ImageCases being documented in version 12. But I immediately desired a mechanism for adding more entities to ...
5
votes
0answers
60 views

How to make the clustering result of version 11.2 and 11.3 same?

I was doing clustering analysis in version 11.2, with codes like below, and then got 12 clusters as the output: ...
5
votes
1answer
304 views

Image Generator with a Neural Network (CIFAR-10)

As some of you may know, CIFAR-10 is a data base which has 60,000 images (which are 32x32 in size) of 10 different categories (airplane, dog, cat, frog, deer, bird, horse, ship, automobile and truck). ...
5
votes
0answers
124 views

What's BayesianMinimization and related functions based on?

Is it specified anywhere what the backend is for the Bayesian optimization related functionality in Mathematica v11? I'm specifically referring to the Bayesian* ...
5
votes
0answers
439 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
0answers
89 views

What algorithm is BayesianMaximization using?

The docs show the following options for BayesianMaximization's Method: "MaxExpectedImprovement" maximize expected improvement over current best value "MaxImprovementProbability" maximize ...
5
votes
0answers
326 views

Softmax Regression Classification Algorithm

I'm following the Stanford Machine Learning course while simultaneously developing my Mathematica abilities. I'm having issues with my Softmax Classifier implementation (for ref, have a look at these ...
5
votes
0answers
112 views

How can I change the distance function in Classify when using NearestNeighbor?

Issue not present in version "10.4.1 for Linux x86 (64-bit) (April 11, 2016)" ...
5
votes
0answers
255 views

Exporting Classify Models

Currently I have created a simple classifier to classify sentiment from a string of text (or a tweet). The code is very basic and looks something like this: ...
4
votes
0answers
40 views

Is there a way to get the decision trees used by machine learning methods like `RandomForest`?

I was looking at a tutorial of SimFin, a new German-based financial data provider. There is a nice example of machine learning using sklearn in python. The package ...
4
votes
0answers
182 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-...
4
votes
0answers
94 views

How to get features for captioned images?

I have a lots of (image, text) pairs and would like to learn a feature extractor (or maybe a FeatureExtractorFunction) for a combined embedding. It seems that when given a list of these multimodal ...
4
votes
0answers
92 views

Can I use Mathematica ML capability to translate an image of a formula?

If I am given a pdf image of a mathematical symbolic formula can I translate it into Mathematica syntax using ML? I tried using Classify, but I can only translate parts of the equation and I don't ...
4
votes
0answers
163 views

Visualizing and Understanding CNN with Mathematica

The famous 2013 paper from Zeiler and Fergus "Visualizing and Understanding Convolutional Networks" proposes a method to understand the behavior of CNN using one (or more) DeConv networks coupled with ...
4
votes
0answers
63 views

How to implement external memory for the “memory augmented neural network”?

I am trying to implement the memory-augmented neural network using MMA 11.3. The memory-augmented neural network in based on the paper here. There are implementations using ...
4
votes
0answers
62 views

Candidate sampling for softmax neural networks in mathematica

Though I've been using mathematica for a few years, I've never really delved into its ML capabilities (except for the occasional clustering). I'm curious if anyone who has some experience using ...
4
votes
0answers
103 views

Capsule Network reconstruction layer

I am experimenting the capsule network, using the architecture provided here: Capsule Network in Mathematica Deep Neural Network Repository While I can figure out what the network do following the ...
4
votes
0answers
95 views

In neural network, how to force the NetTrain to use full batch gradient descent instead SGD?

In a neural network, I want to use full batch gradient descent instead of SGD. Currently, I am using code like this (you can see that I forced BatchSize to be the ...
4
votes
0answers
112 views

How to explain overfitting?

SeedRandom[0]; X = RandomInteger[{1, 5000}, {100000, 50}]; Y = RandomInteger[{0, 1}, 100000]; For net1 and ...
4
votes
0answers
154 views

YOLOv3 Netmodel?

I see that YOLOv2 is on the Wolfram net repo, but has anyone ported the new YOLO version 3 architecture into Mathematica?
4
votes
0answers
377 views

Using Machine Learning techniques for text-analysis

I am analysing a bunch of tweets and I want to understand which political party the authors support. Let say, for example that I have five parties labelled by a number: ...
4
votes
0answers
83 views

Can I use Classify's model without internet or without FrontEnd?

Question1: without Internet When I'm using a model trained by Classify in an Machine/Linux without internet, I got the information: ...
4
votes
0answers
132 views

How to train further in Predict?

Training further means we can get much smaller loss in the training set,and maybe get the smaller loss in the validation set,so this is useful. For example ...
4
votes
0answers
169 views

NetTrain with External GPU?

I'd like to use the new Neural Networks functionalities in v11 on my Macbook Pro, unfortunately, most macs do not have the supported Nvidia cards. However, there is the option for using an external E-...
4
votes
0answers
218 views

Is Mathematica a good choice for a scientific project with Machine Learning?

I'm a chemist with some rudimentary programming skills and in the middle of the year I'll be starting a project concerning machine learning, so, I'm sorry if I'm going to ask two questions in this ...
4
votes
0answers
88 views

Create an adequate 'training set' to train a ClassifierFunction which performs the role of the built-in `SubsetQ`

I am trying to "grow" my own SubsetQ function using Machine Learning methods. My cSubsetQ when given two lists (listA and listB)...
4
votes
0answers
208 views

Classification problem using SVM methods

I am running SVM on mathematica and I a used this code with classes: ...
4
votes
0answers
338 views

How to make distance transform invariant to scale?

I am trying to use a distance transform as a descriptor to encode silhouettes in order to do a shape recognition task. It is clear that distance transform distribution is invariant under rotation and ...
3
votes
0answers
55 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
votes
0answers
163 views

Bug in the classification optimization algorithm for large data sets

I believe that I encountered a bug in Mathematica 12. The Classify[] function throws errors when simultaneously: The training set has significantly above $10^5$ ...