Finding the correct network structure and hyper-parameters is a totally black box in deep learning. There is no rule or … More
Author: Sefik Serengil
Tips and Tricks for GPU and Multiprocessing in TensorFlow
Having a GPU shows the wealth. Today, you should spend thousands of dollars to have a good one. For example, … More
Machine Learning meets Blockchain
Solutions come after problems but exceptionally blockchain is a solution looking for its problems. We cannot find a completely solution … More
Machine Learning Wars: Deep Learning vs GBM
Machine learning studies have unfortunately bi-polarization. Practitioners mostly adopt either deep learning or gradient boosting machines. They might support these … More
Apparent Age and Gender Prediction in Keras
Computer vision researchers of ETH Zurich University (Switzerland) announced a very successful apparent age and gender prediction models. They both … More
Twisted Edwards Curves for Digital Signatures
Edwards curves are pivotal ones in crypto field. The normal form Harold Edwards studied was x2 + y2 = c2 + … More
A Gentle Introduction to Edwards-curve Digital Signature Algorithm (EdDSA)
Elliptic curves are the most challenging topic in crypto field whereas Edwards curves are the hottest topic among elliptic curves. Elliptic … More
A Gentle Introduction to Edwards Curves
In 2007, Harold Edwards introduced a new form for elliptic curves. Thereafter, people interestingly named this form as Edwards Curves. Nowadays, … More
A Step by Step Hill Cipher Example
Hill cipher is a kind of a block cipher method. Actually, it was the first one appearing in the history. … More
Using Custom Activation Functions in Keras
Almost every day a new innovation is announced in ML field. Such an extent that number of research papers published … More
