Day 24

We began in the auditorium this morning to practice our presentations. Overall, it seems like everyone's presentations are pretty good. I gave mine third because I will going third on Thursday. I'm glad I am near the beginning of the schedule because I think it would be difficult for me to focus on the other presentations if I was yet to give mine. My presentation today seemed to go well. I was just over ten minutes (the amount of time each individual presentation is supposed to take before questions), and I only had to make a few minor corrections to my slides (such as adding an acknowledgement page). After all of the presentations were done, it was about 12:00, so Ryan and I ate lunch before going to the lab. I had not been able to run my feature extractor experiment overnight, so I started it when I got to the lab and it is still running now. Hopefully, it will continue to run and the results will be ready tomorrow. Since I already gave my practice presentation in the auditorium, I do not think I will add the feature extractor results to my presentation even if they are done tomorrow. It will be good to have that data in the kLab, but if I were to add the results to my presentation, I would have to take the part about preprocessors out due to the time constraint. Also, I have already practiced my presentation as it is, so I do not want to make huge changes right before Thursday. Today I also worked on the problem with CRF (Conditional Random Field, a postprocessor that had not been functioning properly in my tests). I made changes to the pipeline code to accommodate a new version of CRF created by a grad student. Now we are having a new problem after the changes, so we are still working on a good solution. We'll see how this turns out tomorrow.

Comments

Post a Comment

Popular posts from this blog

Day 5

I began the first experiment of my project today. But first, I prepared by doing some reading on the topic of hyperspectral image classification. I read a paper written by Ron and Dr. Kanan about self-taught feature learning. It discussed two self-taught learning frameworks: the multiscale ICA and the stacked convolutional autoencoder. Much of it was difficult for me to understand because I am new to this topic, but I learned more about self-taught machine learning programs. After I finished reading, I began my first experiment. The first step was to document already written machine learning code and to figure out what that code was doing. I read about the standard Python documentation style, then I began to document the code. This proved to be challenging, because this code implemented many methods from outside of itself, which meant I had to understand those methods as well. Today I learned that understanding and following code that was written by someone else can be just as challeng
Read more

Day 13

Today I continued tests for my classifier experiment. I worked on finding the optimal parameters for the Multi-Layer Perceptron (MLP) classifier. I was trying to determine the best hidden layer shape and weight decay. Hidden layer shape is how many dimensions (layers) of neurons (nodes used for machine learning) there are, and how many neurons are in each dimension. I only began with the knowledge that there would be a maximum of three layers in the hidden layer shape. Weight decay is a value that decreases the weight values after each training iteration to prevent overfitting to the training data. I knew that the best value for weight decay would be 1e-4, 5e-4, or 0. I wrote a program to test different combinations of hidden layer shapes and weight decay values. While these tests were running, I documented some of the classifiers with which I was working, including the MLP classifier. This process helped me to better understand MLP and the other classifiers because it made me work thr
Read more

Day 7

Today, I started by writing my abstract, which is a short summary of the project on which I am working this summer. (The abstract is included in my last post.) To write my abstract, I needed to develop a clear idea of my project. I found that summarizing it in writing actually helped me to better understand what I am doing as a whole. After completing and posting my abstract, I returned to my experiment. I first set out to solve the problem of incorrect dimensions in my data, which I had run into on the previous day. I took out the code that reshaped the data, because the data had to be in their original dimensions for the preprocessing methods to function correctly. However, this meant that I had to rewrite the code that split the data by labels into training and testing categories. I had to use an entirely different strategy than I had been using before. Instead of directly splitting the data into two arrays, I am now creating an array of the indices of the data values in the origina
Read more