Over last semester, I wrote a series of blogs focusing on artificial intelligence and machine learning using artificial intelligence, especially that of image classifications. My independent project aimed to create and improve a convolutional neural network that identifies different categories of grocery. Through the semester, I gained considerable experiences working with Tensorflow, the most popular programming framework for machine learning. I also became proficient in creating and improving the neural network, raising its accuracy over 80 percent.
Yet I realize my lack of advanced knowledge in machine learning theories, and therefore I will be taking an open course this semester. The course, titled Cs231n: Convolutional Neural Networks for Visual Recognition, is an advanced computer science curriculum offered by Stanford University. There are 14 lectures in total and I plan to take one or two every week to finish the course within the semester.
Another part of my independent seminar will be working along with an automated twist lock installer project via family connections. The project itself aims to create a robotic arm that could install and remove twist locks attached to shipping containers. These twist locks are attached to shipping containers on the cargo ships so they will not fall off the ships. When the containers are removed from the ships and are prepared for land transports, these twist locks are to be detached. While the process is usually done by manual labor, the project replaces workers with automated robots and improves the efficiency of the process and avoids the personal risks taken by the workers. I will be responsible for the visual component which identifies the location and type of the twist lock in order to apply the proper removal or installation process. More information will be coming in my next blog.
Through this semester, I will be keeping updating my learning progress on course Cs231n and on the project. Stay tuned and see you next week!
NamHyuk Ahn Follow. “Case Study of Convolutional Neural Network.” LinkedIn SlideShare, 1 May 2016, http://www.slideshare.net/nmhkahn/case-study-of-convolutional-neural-network-61556303.