Ruby chocolate’s distinctive flavour gives the possibility to try out new flavour combinations. Here I discuss the process of making ruby bonbons and a few ingredients that I found match well with ruby chocolate. Contents: Tempering ruby chocolate Making colored chocolate shells Making the bonbons Bonbon fillings 1. Tempering ruby...
Introduction Prostate cancer (PCa) is the one of the most common cancers in the world1 and is graded by pathologist using the Gleason grading system. The grading system was originally made by correlating distinctive patterns in the tissue to patient survival: “The way to develop a histologic classification was to...
Recently, I presented a conference article at SPIE Medical Imaging 2018, as part of my PhD in computational pathology, deep learning and prostate cancer. In this project we tackled the problem of epithelium segmentation using deep learning. It was the first project I worked on within computational pathology. This post...
Recently I started using Home Assistant (HA) as a tool to control the lights in my home. My previous system was based on Homekit and, while working fairly good, lacked tools to further customize the automations. To get more control I switched to HA. One of the first things I...
A few years ago I discovered the fastest option to make chocolate mousse (or at least one that is very easy and takes almost no effort). That recipe uses a siphon for almost instant results. Although it is still the fastest option, I tend to use it less and less...
Eggs and cream are the staple food of (classic) desserts. Flans, crème brûlée, crema Catalana, mousse, are all made with these basic ingredients; sometimes directly but often using a custard base. Though, sometimes dietary requirements (or the need of a challenge) requires us to look for alternatives. The eggs and...
In the previous post I talked about getting started with generative adversarial networks (GANs) and applied these types of networks to the MNIST dataset. In that application we limited ourselves to 1D black-and-white images which are fairly easy for a network to learn. Eventually though, we want to switch to...
Generative Adversarial Networks (GANs) are one of the hot topics within Deep Learning right now and are applied to various tasks, ranging from un/semi-supervised learning to generating images. These networks were originally introduced by Ian Goodfellow et al. in 2014: We propose a new framework for estimating generative models via...