Skip to main content

Week 7

This week I focused more on the planning phase and decided to go about it a different way. my plan now is to build the neural network from scratch purely through the theory I know about how they work as I think I have a good enough understanding to build one. I also have a rough idea of what the actual program is going to look like which is basically just a GUI to run, train and save AIs aswell as change some variables. I've been constructing my own flowcharts to help with the logic of the overall system as well as working through the planning steps for the assignment. I'm hoping to finish the planning shortly and submit it for a draft and tweak it during the week.

Comments

Post a Comment

Popular posts from this blog

Final Post

This past week I've been working on fixing issues with the program to make it run as smoothly as possible. I didn't think I would get the stats for nerds page done and was going to scrap it so I could focus on getting the documentation done and fixing the minor issues so it would be more polished but I decided to do the stats for nerds page anyway and spent the past day and a half working on it. The notable issues from its development were mainly around gathering the data, in which I found some other errors in how I was collecting data such as not updating the data files when quitting the program. But i managed to finish the page as well as the rest of the program. My final solution was reasonably successful in comparison to my proposal and design, the only main things that I wasn't able to achieve was customisation of genome numbers and generation size and stuff like that, but that would have required a lot of digging through files in the libraries I was using to edit th...
Post a Comment
Read more

Week 13

this week I’ve been mainly focused on effectively parallelizing my AI so it can run multiple tests at once and be a lot faster, however I’m having trouble interacting with the neat library in order to do this as during some of its processes I need other functions to help me keep track of different things within the program, so I’ve been trying to work out how to edit the library and I’ll continue to work on that this week and hopefully have a finished AI soon enough.
Post a Comment
Read more

Week 14

This week I kept trying to parallelise my ai but found it quite tricky to edit the libraries functions, as they seemed to be working with each other in some weird ways which meant what I thought should work and made perfect sense was just not working. So I decided it was too late in my project to pursue it more, so I reverted my ai back to running one test at a time and began working on the display for when the ai is being tested. So far I've got some stats blitting next to the test, and this week I'm going to work on getting them scrolling as they need to and maybe get the buttons for the testing display done and working.
Post a Comment
Read more