Skip to content

  • Twitter

  • Youtube

  • GitHub

  • Linkedin

  • Facebook

  • Instagram

  • RSS

  • Mail

Sefik Ilkin Serengil

Code wins arguments

  • Home
  • About Me
  • Publications
  • Courses
  • Talks
  • Consultancy

Author: Sefik Serengil

The Math Behind RSA Algorithm

RSA is still the most common public key algorithm in cryptography world. Even though, applying the algorithm is very easy, … More

crypto, euler, fermat, rsa

Unofficial Guide to Fermat’s Little Theorem

Fermat contributes construction of modern math with well known theorems. Today, we are going to mention the little one. This is … More

fermat, rsa

A Step By Step C4.5 Decision Tree Example

Decision trees are still hot topics nowadays in data science world. Here, ID3 is the most common conventional decision tree algorithm … More

c4.5, decision tree, gradient boosted, id3

Random Initialization in Neural Networks

Neural networks requires to apply several state-of-the-art techniques such as choice of activation function, or network design to push their … More

neural networks, python

How Vectorization Saves Life in Neural Networks

Developers tend to handle problems with conditional statements and loops. This is the number one topic of developers and data … More

neural networks, numpy, python, vectorization

A Step By Step Bitcoin Address Example

A money transfer transaction must include sender and receiver account information and transaction amount. On the other hand, a bitcoin … More

bitcoin, blockchain, elliptic curve, python

Convolutional Autoencoder: Clustering Images with Neural Networks

Previously, we’ve applied conventional autoencoder to handwritten digit database (MNIST). That approach was pretty. We can apply same model to … More

autoencoder, neural networks, unsupervised learning

Autoencoder: Neural Networks For Unsupervised Learning

Neural networks are like swiss army knifes. They can solve both classification and regression problems. Surprisingly, they can also contribute … More

autoencoder, neural networks, unsupervised learning

Handling Overfitting with Dropout in Neural Networks

Overfitting is trouble maker for neural networks. Designing too complex neural networks structure could cause overfitting. So, dropout is introduced to … More

hinton, keras, neural networks, tensorflow

IBM Data Summit 2018 Istanbul Notes

IBM organized a data summit on March 15 in this year. Motto of the organization is plan, manage and optimize. Both … More

data, ibm

Posts navigation

Older posts
Newer posts


Licensed under a Creative Commons Attribution 4.0 International License.

Creative Commons License

You can use any content of this blog just to the extent that you cite or reference

Subscribe to sefiks.com to stay up-to-date with latest posts