Differences

This shows you the differences between two versions of the page.

--- project_people:josh_donckels [2017/10/09 23:49] – jdonckels
+++ project_people:josh_donckels [2017/12/10 20:01] (current) – jdonckels
@@ Line 1: / Line 1: @@
-===== Project Idea =====
+===== Project Concept =====
-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, and a fully-connected layer.  This will have to start off static in the MFM, as passing data would be very difficult otherwise.  This will require five elements that I will go into detail further down this page.
+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.  This will have to start off static in the MFM, as passing data would be very difficult otherwise.  This will require five elements that I will go into detail further down this page.
 ===== Elements =====
   * Neuron:
     * 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, and fully-connection
+    * Deal with all of the computations for the convolution
     * 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 in the specific filter
-  * 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 to go based on where it is going
+  * FC_Neuron:
-  * Path
+    * Neurons for the fully-connected layer, which will used fixed point multiplication to calculate its values.
-    * Will help with guiding the packets to the specified Neuron cluster
+    * There will be four layers of 12, which will each represent a pattern to be classified
-  * Packet
+  * FC_Init_Layer:
-    * Will hold information about 7 pixels, and will follow the path and routers to its destination to deliver the information
+    * Will initialize, reset, and repair the FC_Neurons in each layer
+  * Label:
+    * Will be used to classify the network once it is complete, meaning the FC_Layer_Twelve will create this once the the classification values are complete
-===== 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 =====
@@ Line 35: / Line 27: @@
    * Also will work on fixing a size for the CNN based around a smallish image
+Week 8 Update:
+   * Updated project page to more clearly state what my projects is and my goals
+   * Messed around with trying to get my own images as inputs for tiny_dnn
+   * Researched how small my input images could be for a CNN
+Week 9 Update:
+   *Created Demo video for progress on project
+   *New Title: Object Classification in the Movable Feast Machine
+   *Scaled back project a lot to 3x3 hand made images without padding. So they represent object as the pixel values can only be 0 or 1.
+     * These 3x3 images can contain a dot (1) or a 2-length line (0).
+     * I get a 80% successful classification rate in tiny_dnn with the new CNN structure and these input images
+   *Researched into CNN structures and tested them in tiny_dnn with hand-made images of 9x9, 7x7, 5x5, 3x3, with padding and without
+   *New CNN structure is a 12 layer Convolution layer, that goes into a Fully_connected layer that takes in 12 input and outputs 2 results.
+   *Implemented working convolution layer in MFM, which takes pixels from a image element and will calculate the output from this layer
+   *Created shell for Fully-Connected layer for MFM, contains weights and biases, but nothing else yet.
+   *Scratched communication concept, as I can place all layer in a sort of column fashion, so there is no need for this
+Week 10 Update:
+   *Implemented the fully connected layer
+   *Compared values with weights and results from each layer with the tiny-dnn output, they compared well
+     * The results weren't exact, but I found a bug where the values were changing barely based on certain Neurons exceeding their stages and skipping certain steps
+   * Found some major problems in the weights I was using after testing every single possible input pattern
+     * Will find better weights in week 11
+   * Forgot to put my week 10 update on week 10....
+Week 11 Update:
+   *Found better patterns and shapes to use together, am using a 2x2 box and a horizontal 2 length line
+     * Will look into adding more objects that can still be successfully classified
+     * 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
+   * Tested hitting the network with "radiation", and it failed horribly every time
+   * Working towards getting a reset to work
+     * 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
+   * Added a reset element, as when the Neurons see it, they will reset the network
+   * Created a presentation for this project
+Week 12 Update:
+   *Fixed bug with fully_connected layer when the simulation was going too fast for it to correctly pass the weights
+   *Created scripts to get data from modifying parameters for training in tiny_dnn and then will compare the results to what I get from my pre-trained model
+   *Added different objects, so It can classify up to 5 now, with a much worse percentage...
+   *Wrote the abstract for this project
+Week 13 Update:
+   *Added more rotations and shifts of each shape, and this increased the classification rates for every number of classification patterns
+     * 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, methods, some results, and some sort of conclusion/discussion
+   * 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:
+   *Found a few bugs in the repairing and was able to improve it
+   *Redesigned fully-connected layer, to where it can classify four different patterns at any rotation
+     * 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:
+   *Improved slides, and practiced presenting.
+   *Finished everything and turned it in.