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

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

Oracle Analytics Summit 2018 Istanbul

Oracle Analytics Summit is held in Istanbul on 2018 Mar, 07. I have been attending this summit since 2016. I … More

Solving Elliptic Curve Discrete Logarithm Problem

Elliptic curve cryptography is powerful. Calculating public key from known private key and base point can be handled easily. On … More

Counting Points on Elliptic Curves over Finite Field: Order of Elliptic Curve Group

ECDSA enables to produce signatures faster. Besides, its both signatures and keys are much smaller than adopted alternative options offering … More

Leaky ReLU as a Neural Networks Activation Function

Convolutional neural networks make ReLU activation function so popular. Common alternatives such as sigmoid or tanh have upper limits to … More

Elegant Signatures with Elliptic Curve Cryptography

Elegance is the only beauty that never fades. This is a loving Audrey Hepburn quote. I struggle to adapt this … More

Moving Numbers To Upside Down: Extended Euclidean Algorithm

You might be familiar with the upside down if you watched Netflix series Stranger Things. Eleven shows the underside of … More

Real Time Facial Expression Recognition on Streaming Data

Previously, we’ve worked on facial expression recognition of a custom image. Additionally, we can detect multiple faces in a image, … More

Sinc as a Neural Networks Activation Function

Sinc function is a sinusoidal activation function in neural networks. In contrast to other common activation functions, it has rises … More