Category Archives: PyTorch

Neural Anomaly Detection Using PyTorch

I wrote an article titled “Neural Anomaly Detection Using PyTorch” in the April 2019 issue of Microsoft MSDN Magazine. See https://msdn.microsoft.com/en-us/magazine/mt833411. Anomaly detection, also called outlier detection, is the process of finding rare items in a dataset. Examples include identifying … Continue reading

Posted in Machine Learning, PyTorch

Neural Regression Using PyTorch

I wrote an article titled, “Neural Regression Using PyTorch” in the March 2019 issue of Microsoft MSDN Magazine. See https://msdn.microsoft.com/en-us/magazine/mt833293. The goal of a regression problem is to predict a single numeric value. For example, you might want to predict … Continue reading

Posted in Machine Learning, PyTorch

I Give a Talk About Anomaly Detection Using Neural Clustering with PyTorch

About once a week, I give a short (typically 45 minutes long) talk at the large tech company I work for. I recently gave a talk about . . well, it’s not so easy to explain. Let me try. Anomaly … Continue reading

Posted in PyTorch

Unraveling the Mysteries of a PyTorch LSTM Module

Because PyTorch is so new, there aren’t many code examples to be found on the Internet, and the documentation is frequently out-of-sync with the latest code. I’ve worked with very new, rapidly changing code libraries before and there’s no magic … Continue reading

Posted in Machine Learning, PyTorch | 1 Comment

I Give a Talk About Anomaly Detection Using a Neural Autoencoder with PyTorch

Anomaly detection is a very difficult problem. I’ve been experimenting with a technique that I couldn’t find any research or practical information about. Briefly, to find anomalous data, create a neural autoencoder and then analyze each data item for reconstruction … Continue reading

Posted in Machine Learning, PyTorch

I Give a Talk About Neural Binary Classification Using PyTorch

I gave a talk about creating a binary classification model using the PyTorch neural network library. Most neural network beginners start by learning multiclass classification on the Iris Dataset, where the goal is to predict which of three species (setosa, … Continue reading

Posted in Machine Learning, PyTorch

PyTorch train() vs. eval() Mode

The bottom line of this post is: If you use dropout in PyTorch, then you must explicitly set your model into evaluation mode by calling the eval() function mode when computing model output values. Bear with me here, this is … Continue reading

Posted in Machine Learning, PyTorch