Applying neural networks could be divided into two phases as learning and forecasting. Learning phase has high cost whereas forecasting … More
Category: Machine Learning
Building Neural Networks with Weka In Java
Building neural networks models and implementing learning consist of lots of math this might be boring. Herein, some tools help researchers to … More
Hyperbolic Tangent as Neural Network Activation Function
In neural networks, as an alternative to sigmoid function, hyperbolic tangent function could be used as activation function. When you … More
Backpropagation Implementation: Neural Networks Learning From Theory To Action
We’ve focused on the math behind neural networks learning and proof of the backpropagation algorithm. Let’s face it, mathematical background … More
The Math Behind Neural Networks Learning with Backpropagation
Neural networks are one of the most powerful machine learning algorithm. However, its background might confuse brains because of complex … More
Sigmoid Function as Neural Network Activation Function
Sigmoid function (aka logistic function) is moslty picked up as activation function in neural networks. Because its derivative is easy to demonstrate. … More
Introduction to Neural Networks: A Mechanism Taking Lessons From The Past
Neural Networks inspired from human central nervous system. They are based on making mistakes and learning lessons from past errors. They … More
Exponential Smoothing: A Forecasting Approach Smoke Pleasure Triggered
Smoothing methods basically generalize the time series functions based on previous examples’ seasonal effects and trends. In this way, these methods … More
Data Gives Us Superpowers
I enjoy to follow keynotes of Hilary Mason on Data Science. The title of this post is the sentence of her … More
From Korean War To Data Science and Analytics
I’ve found out about dog fights in Top Gun for the first time. Surprisingly, challenging story about a dog fight strategy developed by … More
