Data Scientist | Technical Writer https://linktr.ee/cankocagil

and why it matters

Image by Zoltan Tasi on Unsplash

Decentralized financial systems are priori introduced with the development of Bitcoin in 2009 by Satoshi Nakamoto who is/are mystery inventor first cryptographic, peer-to-peer electronic cash system that solves the double-spending problem in the context of financial transactions. Bitcoin is backed by blockchain technology that intervenes in the peer-to-peer architecture of…

Thoughts and Theory

Machine Learning & Cognitive Tasks

Visualization of Anatomic fMRI (Image By Author)

Materials

This is the very first article of the series, namely “Cognitive Computational Modelling for Spatio-Temporal fMRI in Ventral Temporal Cortex”. If you want to check out the whole series, go to the following link.

I will introduce the topic of cognitive computational modeling and its use case in the research…

Decentralization is not a liability but an asset of great value

Centralization is a liability not an asset of great value.

The motto “IN GOD WE TRUST” was placed on United States coins largely because of the increased religious sentiment existing during the Civil War. Secretary of the Treasury Salmon P. Chase received many appeals from devout persons throughout the country, urging that the United States recognize the Deity on United…

Non-Convex Optimization from both mathematical and practical perspective: SGD, SGDMomentum, AdaGrad, RMSprop, and Adam in Python

Photo by Lukas from Pexels

This article will provide the short mathematical expressions of common non-convex optimizers and their Python implementations from scratch. Understanding the math behind these optimization algorithms will enlighten your perspective when training complex machine learning models. The structure of this article will be as follows. First, I will talk about the…

From Spatial to Spatio-temporal Visual Processing

Image By mnbb on Getty Images

Instance-based classification, segmentation, and object detection in images are fundamental problems in the context of computer vision. Different from image-level information retrieval, the video-level problems aim at detection, segmentation, and tracking of object instances in spatio-temporal domain that have both space and time dimensions.

Video domain learning is a crucial…

Thoughts and Theory

Generating autonomous captions with visual attention

Sample Generated Captions (Image By Author)

This was a research project for experimental purposes, with deep academic documentation, so if you are a paper lover then go check for the project page for this article

This article will be a nearly direct transition from paper to the article, will cover image captioning tasks using simple yet…

Thoughts and Theory

Joint Object Detection, Instance Segmentation, Object Tracking, and Classification in Video Domain

Example predictions of TT-SRN on arbitrary test video. We intend to point out the occlusions, point view variations, systematic artifact on overlapping objects, and scale of instances. From left upper corner to right lower corner, visuals are sequential predictions of our model. (Image By Author)

You have 5 seconds, tell me what is TT-SRN?

“Fast, simple yet accurate video instance segmentation module based on transformers”

What the heck are the TT-SRN and VIS?

Video instance segmentation (VIS) is the recently introduced computer vision research that aims at joint detection, segmentation, and tracking of instances in the video domain. Recent methods proposed highly sophisticated…

Can Kocagil

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store