Improved Machine Learning

Machine learning in Mathematica 11

Mathematica Version 11 extends and improves its machine learning capabilities. New functions allow users to extract features, reduce dimension, cluster data, optimize hyperparameters, and obtain interpretable models. The feature extraction functionality can be used to visualize datasets or to create semantic distances for search systems. Computer vision is substantially improved: ImageIdentify can recognize more than 10,000 objects, and performances of Classify on images are enhanced. Additionally, machine learning functions accept a wider range of data types.

Key Features

  • Use built-in object recognition on images.»
  • Train your own image identifier.»
  • Extract numerical features from various data types. »
  • Create classifiers from unlabeled data. »
  • Find a hierarchical clustering for a dataset. »
  • Reduce the dimension of a numerical dataset. »
  • Automatically find a formula that fits a curve. »
  • Automatically find a symbolic distribution that fits data.»
  • Optimize parameters using Bayesian optimization. »
  • Train models on mixed data types. »
  • Use the Gaussian process prediction method. »

Related Examples

Create Inactive Symbols and Expressions »

Create an Insect Identifier Tool »

Identify Notable Persons »

Visualize a Dataset Using Feature Extraction »

Derive a Least-Squares Solution »

Create an Image Search Tool Using Feature Extraction »

Find the Distribution of English Words' Frequency »

Find a Formula That Fits Temperature Variations »

Cluster Molecules Based on Their Properties »

Cluster Geyser Eruptions »

Visualize the Predictions of a Gaussian Process Model »

Find the Optimal Parameters of a Classifier »