Sep 12 -19 Journal


First weekly journal! Getting a head start on our Paper Airplane Lab #2, Elizabeth and I did the experimentation for our second lab to optimize plane design for sustainability. We tested this time the Hammer design with the full sheet of paper and quarter sheet of paper. Compared to Lab 1 though, the folding was harder for the Hammer due to much thicker buildups of paper. I also got back my Lab Write Up 1 and learned some of the strengths and weaknesses I had and I revised it for Sunday's revision writeup.


This week, we had our first official Caltech visit with the professors! Though it was only about an hour, I learned a lot from Dr. Hassibi. He tested the waters to see what we already knew but really made an impact through his connections to real world situations. While we had been learning about the math or research process for machine learning, Dr. Hassibi's connection of it to identifying dog breeds or personality quizzes reinforced my fascination with the field. What I learned is summed up in the notes below!


With Dr. Hassibi there to guide us, I felt that he was a unifying force due to his questions about what we have been doing revealing to us how independent study has created a lack of unity in the group knowledge and focus. With this new perspective though, the machine learning group and I talked with Mr. Lee and we brought about an updated approach to the concept map work for the class! Basically now we are all learning one concept together and splitting it into subconcepts for the writing AFTER we all learn together. Everyone knows all the subconcepts but they are split up depending on the situation. This talk really soothed some of my worries as I would know about Mechanical Turk and nothing about Tensor Flow while for someone else it would be the complete opposite.


With the new approach to the concept map, the Hassibi group and I began looking into the concept of linear regression (video below). The two videos below offer some information in regards to an introduction and specific part of the concept. This group approach where all of us sat around Connie's computer and learned from that screen really solidified the sense of teamwork and I think that this approach fits me the best. We all were there to learn and ask one another questions when we had any.
While learning about linear regression, a moment that was really fulfilling was being able to apply and teach the aspect of derivatives and the current calculus I am learning to another teammate (showed in the below video on Gradient Descent). It showed not only the collaboration of the group but also how research in machine learning is definitely interdisciplinary. It was very satisfying to see my work in another class have applications in this one!



That's all for this post! See you all next week!

Comments

Post a Comment

Popular posts from this blog

April 10 Technical Journal

Image
Code: Working right now as sort of a middle man between the Q learning and code sides, I was helping out a bit with the code as well since the last technical journal on March 13. While I am still mainly focused on the Q learning side, I worked with Edmond on how to improve user interaction with our game. This would come in the form of changing how the lines are inputted. Our current game requires us to input coordinate points to create lines and our new idea is to designate certain coordinates' pairings as a number (depicted below). For example, the line connecting (0,0) and (1,0) is 1. The pattern would be like a zig zag. Q Learning Algorithm: Continuing on the reinforcement learning look into the Q learning algorithm, Connie and I were working with code we got off of Github which stored Q values in a Q table file. Running it over the period, a statement of "Kolo #,#" was printed. The number started off very unbalanced with the first at 0 and the second at 99. Ove...
Read more

March 13 Technical Journal

Image
Tic Tac Toe Data: We first planned on spending this two weeks looking into datasets for tic tac toe and processing it as a pre-trial for our dots and boxes. What we found and did though, I though was far more insightful. Initially, I was looking around for datasets and found from UVA a dataset for tic tac toe intermediate game states. We thought this could be something as the UCI dataset that we had first come across only gave endgame states. An image of the UVA dataset is posted below. Discussing with Mr. Lee, though, we could not decipher what the non-zero/one numbers represented and decided to move on looking, a sort of dead end. We inferred that -1 and 1 were X and O while 0 was blank. We would eventually later find another way to gather datasets (see Tic Tac Toe Q Learning below). Part of Tic Tac Toe intermediate game states data Tic Tac Toe Monte Carlo: While we had been looking into datasets, it turns out that Will was experimenting with the Monte Carlo search tre...
Read more

Start of School - Sep 12 Journal

Image
Through these several weeks, we have begun our journey to exploring research in machine learning by starting our paper airplane research project, hearing undergraduate research presentations, and learning the foundations of machine learning and the basic principles of research.  Foundations: Our first several weeks covered the foundations of research and more specifically machine learning. In a class activity, all the groups came up with several truths about research and the class was able to collectively develop a set of rules and expectations for the research journey. From "always keep on trying" to "look to nature for inspiration," many of these truths resounded with me as I hope to learn more about this field via research in this course.  The foundations of machine learning were also covered through a series of videos. From explaining neural networks to linear regression, these videos established a baseline from which my group and I could work o...
Read more