Books (By Me!)
Events (I Speak At!)
-
Recent Posts
Archives
Categories
Category Archives: PyTorch
PyTorch TransformerEncoder Reconstruction Error Anomaly Detection for Ordered Data
A fairly well known anomaly detection technique uses a neural encoder-decoder (aka autoencoder) combined with reconstruction error. A few weeks ago, I experimented by inserting a TransformerEncoder module into such a system and the results seem promising. However, transformer architecture … Continue reading
Posted in PyTorch, Transformers
Leave a comment
Time Series Regression Using a Standard Neural Network With PyTorch
Time series regression (TSR) problems are very challenging. There are dozens of techniques — and the mere fact that there are so many techniques for TSR indicates the difficulty of these problems and that there’s no single best approach. There’s … Continue reading
Posted in PyTorch
2 Comments
Creating Some Synthetic Medical Data
I’ve been working on some ideas for advanced data anomaly detection that involves using a deep neural autoencoder that is augmented with a TransformerEncoder module. Because a TransformerEncoder processes each input vector (typically a sentence) as a sequence that has … Continue reading
Posted in PyTorch, Transformers
Leave a comment
Running a PyTorch Program on Colab from a MacOS Machine
I sometimes present PyTorch training sessions at my workplace or at technical conferences. By far the biggest pain point is dealing with attendees’ PyTorch installations. So I’ve been investigating the feasibility of using the online Colab system. Briefly, Colab is … Continue reading
Posted in PyTorch
Leave a comment
Installing PyTorch 2.0.0 on Windows 10/11
PyTorch is a neural network code library. By far the biggest hurdle for beginners is installation. Note: These instructions also work for other PyTorch versions such as 1.13.1 and 2.1.0 and 2.2.1 — just different .whl files (see below). These … Continue reading
Posted in PyTorch
Leave a comment
Installing Anaconda3 2022.10 with Python 3.9.13 on Windows 10/11
Anaconda is a collection of software packages that contains a base Python engine plus over 650 compatible Python packages. Anaconda version 2022.10 has Python 3.9.13. You need to install Anaconda Python before you can install the PyTorch neural network code … Continue reading
Posted in PyTorch
Leave a comment
Installing Python 3 and PyTorch 2.2.0 on a MacBook Laptop
I most often use Windows OS machines but I sometimes use Mac and Linux machines. It had been several months since I had used the PyTorch neural network library on a Mac machine so one weekend I figured I’d do … Continue reading
Posted in PyTorch
Leave a comment
Simple Perturbation Interpretability for PyTorch Regression
I was looking at the Captum library for PyTorch model interpretability. I wasn’t entirely happy with Captum because it seems somewhat over-engineered and difficult to modify. So I decided to implement the simplest possible from-scratch interpretability for a PyTorch regression … Continue reading
Posted in PyTorch
Leave a comment
Multiplying Neural Network Weights and Biases By a Constant
I was working on a neural network project recently, and I briefly wondered if it would be feasible to multiply all weights and biases by a constant, such as 2.0. I pretty quickly realized that the idea doesn’t make much … Continue reading
Simple Interpretability for PyTorch Binary Classification
I looked at the Captum library for PyTorch binary classification model interpretability. But I wasn’t entirely happy with Captum because it seems over-engineered and difficult to modify. So I decided to implement the simplest possible from-scratch interpretability for a PyTorch … Continue reading
Posted in PyTorch
Leave a comment
You must be logged in to post a comment.