Demonstrate a thorough understanding of existing legacy base by being able to consistently run the legacy version of the Convolutional Neural Network and display resulting data.
Following our meeting with Ana, our team received what was effectively a 1 GB file dump comprised of a combination of MATLAB, and audio files, as well as a few research papers. After a quick look at the current state of the CNN, we realized how lacking the system was in many aspects. First, it lacked documentation. Other than a word document that came with the program that outlined the process for running the classifier, we had no hints as to how we would start. Further, after having spent a few hours looking at code, it was clear that some files were actually missing. Also, according to Dr. Sirovic, parts of the code had been modified from their original intent. We would have to fix this to get the program running as it had been intended.
Organize a currently scattered legacy code into a singular program that can be run simply and intuitively.
After eventually being able to wholly run the classifier, we intend to organize and improve the legacy code’s design. This process also includes writing documentation for the sake of future developers. Once organized, it should be much easier to modify the code so that the process of training, running, and even testing the classifier is far more streamlined. This will significantly enhance the viability of the CNN as a research tool. Ideally, by this stage we would be able to deliver a singular executable program that Ana and others at Scripps can use efficiently.
Develop a Graphical Interface for the Convolutional Neural Network that will improve usability.
Our team aims to deliver a single executable program that can be used by Dr. Sirovic at a presentation three weeks following the end of the quarter. While the deliverable described in Milestone 2 would be sufficient, we believe a graphical interface that handles the different usage cases for the classifier would significantly improve usability while being more presentable at the aforementioned conference.
Familiarize ourselves on the topic of CNNs by writing a simple report outlining our knowledge and determining proper metrics for measuring performance of the CNN we will be developing as the development process continues.
Upon entering this project, our team lacked in knowledge about Convolutional Neural Networks, so approaching this project would be challenging. We decide to do numerous research on this topic and relate back to our project. Additionally, we will write a simple report outlining our findings on CNNs.
After having discussed with Dr. Sirovic and the rest of the team, we believe it is a real possibility that we will continue contributing to the development of the Convolutional Neural Network following the end of the quarter. In this case, some milestones we have discussed include: Open sourcing and generalization of the classifier so that it can be used as a tool in a wide range of fields; Determining metrics for classifier performance and subsequently attempting to improve performance based on the determined metrics; Looking into other projects at Scripps.
Demonstrate a thorough understanding of existing legacy base by being able to consistently run the legacy version of the Convolutional Neural Network and display resulting data.
Following our meeting with Ana, our team received what was effectively a 1 GB file dump comprised of a combination of MATLAB, and audio files, as well as a few research papers. After a quick look at the current state of the CNN, we realized how lacking the system was in many aspects. First, it lacked documentation. Other than a word document that came with the program that outlined the process for running the classifier, we had no hints as to how we would start. Further, after having spent a few hours looking at code, it was clear that some files were actually missing. Also, according to Dr. Sirovic, parts of the code had been modified from their original intent. We would have to fix this to get the program running as it had been intended.
Organize a currently scattered legacy code into a singular program that can be run simply and intuitively.
After eventually being able to wholly run the classifier, we intend to organize and improve the legacy code’s design. This process also includes writing documentation for the sake of future developers. Once organized, it should be much easier to modify the code so that the process of training, running, and even testing the classifier is far more streamlined. This will significantly enhance the viability of the CNN as a research tool. Ideally, by this stage we would be able to deliver a singular executable program that Ana and others at Scripps can use efficiently.
Develop a Graphical Interface for the Convolutional Neural Network that will improve usability.
Our team aims to deliver a single executable program that can be used by Dr. Sirovic at a presentation three weeks following the end of the quarter. While the deliverable described in Milestone 2 would be sufficient, we believe a graphical interface that handles the different usage cases for the classifier would significantly improve usability while being more presentable at the aforementioned conference.
Familiarize ourselves on the topic of CNNs by writing a simple report outlining our knowledge and determining proper metrics for measuring performance of the CNN we will be developing as the development process continues.
Upon entering this project, our team lacked in knowledge about Convolutional Neural Networks, so approaching this project would be challenging. We decide to do numerous research on this topic and relate back to our project. Additionally, we will write a simple report outlining our findings on CNNs.
After having discussed with Dr. Sirovic and the rest of the team, we believe it is a real possibility that we will continue contributing to the development of the Convolutional Neural Network following the end of the quarter. In this case, some milestones we have discussed include: Open sourcing and generalization of the classifier so that it can be used as a tool in a wide range of fields; Determining metrics for classifier performance and subsequently attempting to improve performance based on the determined metrics; Looking into other projects at Scripps.