Changes between Version 67 and Version 68 of Other/Summer/2023/Features
- Timestamp:
- Aug 9, 2023, 7:21:31 PM (11 months ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
Other/Summer/2023/Features
v67 v68 12 12 [[span(style=color: #A50000, '''Advisors''')]] - Dr. Richard Howard, Dr. Richard Martin 13 13 14 === Summer 2023 Poster15 16 [[Image(NN_poster.pptx.png, width=1200, height=1000)]]17 18 14 === Project Description 19 15 20 16 Neural networks have a long history of being used for classification, and more recently content generation, Example classifiers including, image classification between dogs and cats, text sentiment classification. Example generative networks include those for human faces, images, and text. Rather than classification or generation, this work explores using networks for feature analysis. Intuitively, features are the high level patterns that distinguish data, such as text and images, into different classes. Our goal is to explore bee motion datasets to qualitatively measure the ease or difficulty of reverse-engineering the features found by the neural networks. 17 18 21 19 22 20 === Week 1 Progress … … 42 40 [[Image(unnamed.jpg, width=200, height=200)]] First Prototype -> [[Image(jitterbug2.gif, width=200, height=200)]] Applying "Power Law" -> [[Image(0.0.gif, width=200, height=200)]] 43 41 42 https://docs.google.com/presentation/d/1CUsZIpquM0ZV0PSCLitq5EsfMTJz4iVAQ4b3pk8_gQI/edit#slide=id.g20a62be0e34_0_0 43 44 44 === Week 3 Progress 45 45 … … 54 54 [[Image(Screen Shot 2023-07-19 at 10.44.07 AM.png, width=400, height=125)]] [[Image(Screen Shot 2023-07-19 at 10.46.33 AM.png, width = 200, height = 100)]] 55 55 56 https://docs.google.com/presentation/d/1_dZirzqPIkBOsUDAHdJSiHIpVgf-TdTRbP-K97CZeXM/edit#slide=id.g255fda0ef8b_0_458 57 56 58 === Weeks 4 and 5 Progress 57 59 … … 61 63 62 64 * **Reformat tar files: ** We altered the program to reformat the training data. Instead of combining the frames of the random bee simulator into a video format, we compiled the data into a tar file, which consists of a png, a class, and a metadata file for each frame in the simulation. We will use these tar files as training data for the model. 65 66 https://docs.google.com/presentation/d/10LL2DQ5wy2e9MNfBmUn3hnLoixhM3UpnMleaLXY5jwk/edit#slide=id.g2587e9ef81d_0_172 63 67 64 68 === Week 6 Progress … … 72 76 [[Image(anticlockwise.gif, width=350, height=300)]] [[Image(clockwise.gif, width=350, height=300)]][[Image(Screen Shot 2023-07-19 at 12.23.26 PM.png, width=350, height=300)]] 73 77 78 https://docs.google.com/presentation/d/13kuM64opDaoH3wVpFatiwiS7849zpjlLzW0q8wsVIVM/edit#slide=id.g259118e31d9_0_229 79 74 80 === Week 7 Progress 75 81 … … 79 85 80 86 [[Image(yesbias_AdobeExpress.gif, width=300, height=300)]][[Image(nobias_AdobeExpress.gif, width=300, height=300)]] 87 88 https://docs.google.com/presentation/d/14P4f2n2sCoIkeknVfsmpHFdldTG9xznclu4V_xbCtFc/edit#slide=id.g25a7ea5071e_0_229 81 89 82 90 === Week 8/9 Progress … … 90 98 [[Image(Screen Shot 2023-08-07 at 3.11.34 PM.png, width=350, height=300)]][[Image(Screen Shot 2023-08-07 at 3.22.19 PM.png, width=350, height=300)]] 91 99 100 https://docs.google.com/presentation/d/14_O6oJ1Z98k6zDMZ46I_GgvBa61mNDzJoDTEpYM8tX4/edit#slide=id.g25dd690f981_0_229 101
