project_people:josh_donckels
Differences
This shows you the differences between two versions of the page.
| Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
| project_people:josh_donckels [2017/11/03 03:49] – jdonckels | project_people:josh_donckels [2017/12/10 20:01] (current) – jdonckels | ||
|---|---|---|---|
| Line 1: | Line 1: | ||
| - | ===== Project | + | ===== Project |
| - | Implement a convolutional neural network (CNN) that will be able to classify an input image. It will use the layers based around a very basic CNN including: convolution layer, pooling layer, rectifier layer, | + | Implement a convolutional neural network (CNN) that will be able to classify an input pattern (a 3x3 window on the MFM). It will use the layers based around a very basic CNN including: convolution layer and a fully-connected layer. |
| ===== Elements ===== | ===== Elements ===== | ||
| * Neuron: | * Neuron: | ||
| * Will contain the weights from the pre-trained network that it will be using to classify the image | * Will contain the weights from the pre-trained network that it will be using to classify the image | ||
| - | * Deal with all of the computations for the convolution, pooling, normalization, | + | * Deal with all of the computations for the convolution |
| * Will update the neighboring pixels based on the output from the computation | * Will update the neighboring pixels based on the output from the computation | ||
| - | * Pixel | + | * Init_Layer: |
| - | * Holds the gray-scale value for 7 pixels, then has space for a couple more bits for flags in the future | + | * This is the middle Neuron, which will initialize, reset, and repair all of the other Neurons |
| - | * Router | + | * This will also contain its own weight, and bias which will be summed into the total from the filter |
| - | * Will hold routing information based on which way for a packet | + | * FC_Neuron: |
| - | * Path | + | * Neurons |
| - | * Will help with guiding | + | * There will be four layers of 12, which will each represent |
| - | * Packet | + | * FC_Init_Layer: |
| - | * Will hold information about 7 pixels, and will follow | + | * Will initialize, reset, and repair |
| + | * Label: | ||
| + | * Will be used to classify the network once it is complete, meaning the FC_Layer_Twelve | ||
| - | ===== Goals ====== | ||
| - | * Main Goal: Run a simple MNIST example with smaller training set of 0's, of image size 18x18(?) | ||
| - | * First Step: Get a layout that will work for the CNN (X) | ||
| - | * Second Step: Get 7 packets sent from one cluster of pixels to another cluster of pixels ( ) | ||
| - | * Third Step: Get pixel packets from all other clusters of pixels to one Neuron cluster, then run that specific convolution layer over all pixels from the image ( ) | ||
| - | * Fourth Step: Get the above goal to work with all clusters of Neurons ( ) | ||
| - | * Fifth Step: Implement the pooling step ( ) | ||
| - | * Sixth Step: Set-up the rectifier layer ( ) | ||
| - | * Seventh Step: Create the fully-connected outcome ( ) | ||
| - | * Eight Step: Classify the image ( ) | ||
| ===== Weekly Logs ===== | ===== Weekly Logs ===== | ||
| Line 62: | Line 54: | ||
| Week 11 Update: | Week 11 Update: | ||
| | | ||
| - | * Will look into assing | + | * Will look into adding |
| * Implemented these weights and biases into the project, and it classifies 8/10 possible patterns (6 from the horizontal 2 length line, and 4 from the 2x2 box) | * Implemented these weights and biases into the project, and it classifies 8/10 possible patterns (6 from the horizontal 2 length line, and 4 from the 2x2 box) | ||
| * Does not pull the image (pixels) from a element anymore, now can be hand drawn by the user | * Does not pull the image (pixels) from a element anymore, now can be hand drawn by the user | ||
| Line 69: | Line 61: | ||
| * The neurons in the convolution already had their weights stored separately from their output values, whil the fully connected layer did not | * The neurons in the convolution already had their weights stored separately from their output values, whil the fully connected layer did not | ||
| * I have successfully separated the weights and the output values for the fully-connected layer, and it works perfectly | * I have successfully separated the weights and the output values for the fully-connected layer, and it works perfectly | ||
| - | + | * Added a reset element, as when the Neurons see it, they will reset the network | |
| + | * Created a presentation for this project | ||
| + | |||
| + | Week 12 Update: | ||
| + | | ||
| + | | ||
| + | | ||
| + | | ||
| + | |||
| + | Week 13 Update: | ||
| + | | ||
| + | * Can no only classify 4, but way better percentages up by about 20-30% from the previous version | ||
| + | * Also found a problem with the version I was using in tiny-dnn, but was able to fix it. Was having to do with the rescaling of the outputs | ||
| + | * Created more plots with the improved numbers and places them in my paper | ||
| + | * Added a lot more to my paper including introduction, | ||
| + | * Corrected my abstract | ||
| + | * Fixed my CNN in the MFM to be more robust, where when a big chunk is removed it will repair itself, and then when a reset is used it can be re-run | ||
| + | |||
| + | Week 14 Update: | ||
| + | | ||
| + | | ||
| + | * Box, two-length line, L shape, and a three-length line, I get a global max of 77.5% class rate | ||
| + | * Went back to three as I was running into problems and I get consistent 85% classification rate | ||
| + | * Improved paper, still need more plots for results and an improved discussion | ||
| + | * Finished Paper! | ||
| + | |||
| + | Week 15 Update: | ||
| + | | ||
| + | | ||
| + | |||
| + | |||
| + | |||
project_people/josh_donckels.1509680981.txt.gz · Last modified: 2017/11/03 03:49 by jdonckels