Julian Francis, a longtime user of the Wolfram Language, contacted us with a potential submission for the Wolfram Neural Net Repository. The Wolfram Neural Net Repository consists of models that researchers at Wolfram have either trained in house or converted from the original code source, curated, thoroughly tested and finally have rendered the output in a very rich computable knowledge format. Julian was our very first user to go through the process of converting and testing the nets.We thought it would be interesting to interview him on the entire process of converting the models for the repository so that he could share his experiences and future plans to inspire others.
The Mathematics Genealogy Project (MGP) is a project dedicated to the compilation of information about all mathematicians of the world, storing this information in a database and exposing it via a web-based search interface. The MGP database contains more than 230,000 mathematicians as of July 2018, and has continued to grow roughly linearly in size since its inception in 1997.In order to make this data more accessible and easily computable, we created an internal version of the MGP data using the Wolfram Language’s entity framework. Using this dataset within the Wolfram Language allows one to easily make computations and visualizations that provide interesting and sometimes unexpected insights into mathematicians and their works. Note that for the time being, these entities are defined only in our private dataset and so are not (yet) available for general use.
✕ net = NetModel["ResNet-101 Trained on ImageNet Competition Data"]
Neural networks are very well known for their uses in machine learning, but can be used as well in other, more specialized topics, like regression. Many people would probably first associate regression with statistics, but let me show you the ways in which neural networks can be helpful in this field. They are especially useful if the data you're interested in doesn't follow an obvious underlying trend you can exploit, like in polynomial regression.
In a sense, you can view neural network regression as a kind of intermediary solution between true regression (where you have a fixed probabilistic model with some underlying parameters you need to find) and interpolation (where your goal is mostly to draw an eye-pleasing line between your data points). Neural networks can get you something from both worlds: the flexibility of interpolation and the ability to produce predictions with error bars like when you do regression.
Recognizing words is one of the simplest tasks a human can do, yet it has proven extremely difficult for machines to achieve similar levels of performance. Things have changed dramatically with the ubiquity of machine learning and neural networks, though: the performance achieved by modern techniques is dramatically higher compared with the results from just a few years ago. In this post, I'm excited to show a reduced but practical and educational version of the speech recognition problem---the assumption is that we’ll consider only a limited set of words. This has two main advantages: first of all, we have easy access to a dataset through the Wolfram Data Repository (the Spoken Digit Commands dataset), and, maybe most importantly, all of the classifiers/networks I’ll present can be trained in a reasonable time on a laptop.
It’s been about two years since the initial introduction of the Audio object into the Wolfram Language, and we are thrilled to see so many interesting applications of it. One of the main additions to Version 11.3 of the Wolfram Language was tight integration of Audio objects into our machine learning and neural net framework, and this will be a cornerstone in all of the examples I’ll be showing today.
Without further ado, let’s squeeze out as much information as possible from the Spoken Digit Commands dataset!