RSSAmplifier

Blog

Audun M Øygard

auduno.github.ioRSS feed ↗12 posts

Latest posts

Visualizing an art collection

.paintings { text-align:center; } .painting { display:inline-block; padding-left:5px; padding-right:5px; } .dcgan { width:200

Peeking inside Convnets

Convolutional neural networks are used extensively for a number of image related tasks these days. Despite being very successful, they're

Drawing with GoogLeNet

In my previous post , I showed how you can use deep neural networks to gene

Visualizing GoogLeNet Classes

Ever wondered what a deep neural network thinks a Dalmatian should look like? Well, wonder no more. Recently Google <a href="http

Estimation in Sequential Analysis

In the previous post I introduced the Sequential Generalized Likeli

Rapid A/B-testing with Sequential Analysis

A common issue with classical A/B-tests, especially when you want to be able to detect small differences, is that the sample size needed can be prohibitively large. In many cases it can take several weeks, months or even years to collect enough data to conclude a test. In this post I&rsquo;ll introduce a very little known test that in many cases severely reduces the number of samples needed,…

Some nice ML-libraries

I recently had a go at the Kaggle Acq

Twisting faces

In the previous post , I explained how <a href="https://github.com/auduno/clmtrackr" target=

Fitting faces

A while ago I put out a semi-finished version of CLMtrackr</

Building a budgeting service

As I wrote in my last blog post , around 3 years ago I decided to try to buil

Building a budgeting service

So, it&rsquo;s been over a year since I &ldquo;took a break&rdquo; from working on my stealth startup project, and I guess it&rsqu

Head tracking with WebRTC

<iframe src="https://player.vimeo.com/video/44049736" width="500" height="281" frameborder="0" webkitallowfullscreen="" mozallowfullscreen="