Author Archives: serengil

Hello, TensorFlow!

I proudly announce that I’ve been starting to capture my first online course TensorFlow 101: Introduction to TensorFlow.

Actually, I have been planning to create an online course material for a long time. That’s why; I am so excited right now. On the other hand, accomplishing a long term course is not easy task, I know.

I read a book one day and my whole life was changed. That’s the opening sentence of Orhan Pamuk‘s The New Life. This sentence can be adapted into my life with small modifications.

Previously, I’ve attended Prof. Andrew‘s Machine Learning course on Coursera. I have been met with MOOC through that course. It has taken almost 5 months and I can only focus on the course after working hours. But, I was motivated and feeling ambitious. Finally, I accomplished. That course was a touchstone in my career path. After then, my title which was Software Developer has changed as Data Scientist. BTW, I think a Data Scientist who has a software developer background would get the upper hand on someone else. To sum up, I attend a course one day and my whole life was changed. As a matter of fact, this inspiration triggers me to create this course

The course content will be always free and accessible at my YouTube channel. Moreover, I will share source codes while capturing the course on my GitHub profile. Also, I will capture and add new videos for the course.


Keep calm and be a youtuber

I hope the course content to be beneficial and contribute your machine learnig adventure. Herewith, I am a youtuber now!

Thanks a lot in advance for your interest.

Becoming the MacGyver of Machine Learning with Neural Networks

You would most probably remember MacGyver if you are a member of generation Y. He is famous for creating materials around him to solve unordinary solutions he faced with. Swiss army knife and duct tape would most probably be used in his practical solution. So, neural networks would be your swiss army knife in machine learning studies.


Richard Dean Anderson appears in series as MacGyver

Previous experiments determine machine learning study to be handled as supervised or unsupervised.

Segmentation is a type of unsupervised learning. In this field, related group of an instance would be looked for. For example, a gym can group customers as fat and thin. However, segmentation method can be based on customer weights, body mass index or muscle and body fat ratio. In other words, there is no correct way for solution. A customer can be involved in different segments in different studies.

In contrast, labels for instances are exact in supervised learning. Suppose that you are working on dead loans. Outstanding ones of given loans are already known.

Continue reading

Homer Simpson Guide to Backpropagation


Homer Simpson has a low IQ of 55

Backpropagation algorithm is based on complex mathematical calculations. That’s why, it is hard to understand and that is the reason why people have an edge on neural networks. Adapting the concept into the real world makes even Homer Simpson easier to figure out. In this post, we’ll mention how to explain backpropagation to beginners.

What if an approved loan application would be outstanding loan (or dead loan)? The bank loses money. So, how can this financial institution derive lesson from this mistake?

Loan application is a process. In other words, an application is required to be examined by multiple authorized employees respectively. For instance, a customer makes an application to bank branch agent, then agent delivers the application to branch supervisor or branch manager. After then, head office employees examine the application when branch manager approved. To sum up, a loan application follows a path and comes to hands of in charged of employees. Should these employees responsible for the lose? The answer is yes based on backpropagation.

Backpropagation algorithm proposes to reflect the lost money amount on the same path, but backwardly. That’s why, it is named as back-propagation. Fine head office employees first, then punish branch manager, supervisor, and agent respectively. What’s more, how much the total lose amount should be reflected to a branch agent? Total lose amount should be divided between in charged of employees based on their contributions on total lose. (Actually, that is the derivative of total lose amount with respect to the employee. E.g. ∂TotalLoseAmount / ∂BranchAgent).  In this way, these employees would be more careful in the next time. That is the principle of backpropagation algorithm. Thus, examination process would progress in time.

As the phrase goes, backpropagation advices slapping ones who are on the tracked path backwardly and in the ratio of their contribution on total error. I would like to thank Dr. Alper Ozpinar for this metaphor.


Batman backpropagates Robin

How Data Science Once Saved the World

Cholera is a killer epidemic disease and it can cause passing away within hours after first symptons of disease appear. Ten thousands of British people died because of cholera between 1831 – 1854. In those days, cholera was thought to be spread by bad air until John Snow proves the disease is spread by the dirty water. However, convincing people about changing this accepted opinion is not an easy task for him although he is a British doctor. Snow believed that sewage contamination into the water was cause of the disease outbreak.


In 1854 Aug, London was again hit by a outbreak of cholera. Outbreak makes sick more than 500 people who live in London in 10 days. Snow negotiated with City Hall and closed street-pumps off in Broad Street. That night nobody died anymore in Broad Street.

Continue reading

Step Function as a Neural Network Activation Function

Activation functions are decision making units of neural networks. They calculates net output of a neural node. Herein, heaviside step function is one of the most common activation function in neural networks. The function produces binary output. That is the reason why it also called as binary step function. The function produces 1 (or true) when input passes threshold limit whereas it produces 0 (or false) when input does not pass threshold. That’s why, they are very useful for binary classification studies.


Heaviside Step Function Dance Move

Human reflexes act based on the same principle. A person will withdraw his hand when he touces on a hot surface. Because his sensory neuron detects high temperature and fires. Passing threshold triggers to respond and withdrawal reflex action is taken. You might think true output causing fire action.

Continue reading

Signing Contents Digitally: An Email Implementation

“I was happy when I design my own signature. Also, deciding to put my signature under this job makes me happier. Characteristic of signatures transforms in time. However, it would be remain same in a day. Letters takes the form of yourself, they makes your name official on a paper”. That’s the cover text of Turkish Singer Sila‘s album named as signature.

Handwritten signatures proves identity of signer on a marked document. Characteristics of letter formation are unique for every person like finger prints. Also, one’s fine motor skills might affect his handwriting. This leaves clues about signatory’s idendity. So, signatures can be verified by Questioned document examination.

Digital signatures are like handwriten signatures. They demonstrates authenticity of digital content and they can be verified too.

Digital signatures include two different cryptography concepts: cryptographic hash functions and public key cryptography.


Hash functions are one way irreversible functions

Continue reading

Exchanging Encrypted Mails

2016 released Snowden is a biographical movie fictionalised life story of Former NSA employee Edward Snowden. The movie reveals illegal surveillance techniques of the government organization. Also, harversting email and search history data is revealed by Snowden, too. This paranoia might convince Zuckerberg. He covered his webcam and mic with tape.

Beyond the paranoia, doubt often forces more rigorous scientific analysis and leads discoveries. In other words, thoroughly conscious ignorance. So, we can protect mails even if they are harvested by third parties. In this post, we will mention an implementation of exchanging encrypted mails.

We will build an exchanging encrypted mail implementation, and run it via gmail infrastructure. In order to work on gmail, you need to allow less secure applications to access your gmail account. You should skip this step if you work on an alternative mail server. Also, we would develop this implementation by referencing Java Mail API.

Continue reading