Puget Systems News
The post will implement Multinomial Logistic Regression. The multiclass approach used will be one-vs-rest. The Jupyter notebook contains a full collection of Python functions for the implementation. An example problem done showing image classification using the MNIST digits dataset.
Whenever I'm feeling confident that I'm successfully contributing to raising five children, my 13-year old daughter does something to jolt me back to reality. That the was the case this week as I sat in the car and gently honked the horn as a reminder she was going to be late for dance practice.
Posted in Featured Systems on 08/16/2017
Our NVIDIA DIGITS machine learning configurations are single CPU, multi-GPU workstations optimized for deep-learning workloads. These are great platforms for working with Caffe and Torch and the DIGITS web interfacea as well as other frameworks like Tensorflow, MXNet, etc.. We have two base recommendations to meet performance and budget requirements.
This post will be mostly Python code with implementation and examples of the Logistic Regression theory we have been discussing in the last few posts. Examples include fitting to 2 feature data using an arbitrary order multinomial model and a simple 2 class image classification problem using the MNIST digits data.
Every time a new generation of CPUs is announced, I see a number of people writing about how they think it will be faster (or slower) than current technology because of the advertised specifications. CPU specs alone don't tell the whole story, though, and comparing core count and clock speed across different brands or generations of processors is extremely misleading. Stop doing it!
In this post I'll discuss evaluating the "goodness of fit" for a Logistic Regression model and do an implementation of the formulas in Python using numpy. We'll look at an example to check the validity of the code.
I got in line at the Starbucks' drive-thru yesterday for my iced caramel macciato. While waiting, I noticed a familiar scene play out. This is a scene I've watched dozens of times since Tesla placed a Supercharger station in the Starbuck's parking lot: Tesla owners chatting with each other.
We test a lot of software here at Puget Systems, and in most cases what we are looking for is what hardware lets a given program run the fastest - or in some cases, what is the most cost effective. If you can get 95% of the best possible performance for half the price that it would cost to get a full 100%, for example, that is often a compelling way to go. However, ANSYS Mechanical (and FLUENT) present a different challenge: how can you get the best performance within the limitations of the ANSYS licensing model?
In this post I will look at "Regularization" in order to address an important problem that is common with implementations, namely over-fitting. We'll go through for logistic regression and linear regression. After getting the equations for regularization worked out we'll look at an example in Python showing how this can be used for a badly over-fit linear regression model.
Are you interested in a clean install of Windows 10? Or maybe you just want to improve system performance and reliability but retain files and folders? This guide will simplify the Windows 10 reset process to help get your system back on track. Please make sure your data is sufficiently backed up before hand!
Logistic regression is a widely used Machine Learning method for binary classification. It is also a good stepping stone for understanding Neural Networks. In this post I will present the theory behind it including a derivation of the Logistic Regression Cost Function gradient.
Regardless of why you are considering moving from Mac to PC, we understand that you probably have a host of questions and concerns. In this article, we want to address a number of questions we get asked over and over from people looking to make the move to PC.
If you are a photo or video editor wondering if you should go with 8-bit or 10-bit hardware, this article is for you!
This will be the last post in the Linear Regression series. We will look at the problems of over or under fitting data along with non-linear feature variables.
Over the past few years, customers have asked us to recommend a service for sharing large files. In the past I've recommended Dropbox to those sending files under 2GB. But what if you need to send a really large file, say a 50GB file? And what if you need to send that 50GB file to five people in different locations?
In this article we will be examining how the new Skylake-X and Kaby Lake-X CPUs on X299 compare to the previous generation Intel CPUs and AMD's Ryzen CPUs in Unreal Engine Editor.
I was recently having some issues with my cable internet and TV. At first, the cable box would periodically freeze and we'd be unable to change the channel. About the same time, the internet would cut out as well too. At first, it was only happening a couple of times a week. Eventually, it started happening a couple times a day.
In this article we will be examining how the new Skylake-X and Kaby Lake-X CPUs on X299 compare to the previous generation Intel CPUs and AMD's Ryzen CPUs in After Effects.