Projects

cmpt310-autumn2006-assignment5

Fall 2006 CMPT 310: Introduction to Artificial Intelligence Instructor: Greg Mori Assignment 5: Learning Due Dec. 4 at 11:59pm This assignment can be done in pairs. Important Note: The univeristy policy on academic dishonesty (cheating) will be taken very seriously in ... [More] this course. Students will work in pairs on this assignment. You may not discuss the specific questions in this assignment, nor their solutions with any other group. You may not provide or use any solution, in whole or in part, to or by another group. You are encouraged to discuss the general concepts involved in the questions in the context of completely different problems. If you are in doubt as to what constitutes acceptable discussion, please ask! Further, please take advantage of office hours offered by the instructor and the TA if you are having difficulties with this assignment. Part 0: Handwritten Digits Download the images from the course website. There are two paths to follow, the MATLAB path (which I believe to be easier), and the Java path (which you may be much more familiar with). Choose one of the following: 1. Tarball 1.1 (data java.tar.gz) contains a huge set of 60000 training images, examples of handwritten digits. The binary file format is a pair of integers giving the height h and width w of the image, followed by a list of hw integers. Tarball 1.2 (code java.tar) contains code for reading in these images, written in Java. Along with the directory of images is a file containing 60000 labels (integers in {0, 1, . . . , 9}) in the same format as the image files h is 60000, w is 1. Again, code for reading these in Java is available. 2. Tarball 2.1 (data matlab.tar.gz) contains 2 data files, and Tarball 2.2 (code matlab.tar) a matlab function for reading in these data files. Running the function [train images, train labels] = readData; will store a 28-by-28-by-60000 array in train images and a 60000-by-1 array in train labels. Each entry train images(:,:,i) corresponds to one image. An image can be viewed by simply typing figure; imshow(train images(:,:,i)). If you do not have large amounts of RAM, instead load train1000.mat (load(’train1000.mat’)), which will load only the first 1000 images and labels into variables train images1000 and train labels1000. If you also don’t have a newer version of matlab which allows compressed .mat files, use load(’train1000v6.mat’) after gunzipping said file. For your viewing pleasure, all 60000 training images have been converted to JPEG format, and are available as a tarball on the course website. It is not recommended that you use these as input to your program, as this JPEG compression is lossy. Part 1: Perceptron Learning Train a single layer perceptron to recognize the digit 7 in your chosen programming language. There should be M = 28 ∗ 28 + 1 = 785 input units (xi ), one for each pixel in an image, plus a bias term (which is set to -1 for all inputs). There is one output unit, which should be trained to be 1 if the image is of a digit 7, and 0 otherwise. Your method should initialize the 785 weights Wj to some random values, and use the Perceptron Learning algorithm to find (locally) optimal weights using gradient descent. Use a subset of the 60000 images to train your perceptron (perhaps the first 100, or first 1000, or first 10000). Pseudocode for perceptron learning: W = random initial values for iter = 1 to T     for i = 1 to N (all examples)         x = input for example i         y = output for example i         Wold = W         Err = y − g(Wold · x)         for j = 1 to M (all weights)            Wj = Wj + α · Err · g′ (Wold · x) · xj For your testing output, show the learned weights Wj (without the bias term) as an image (use reshape(W(1:end-1),[28 28]) in MATLAB, or write a pgm image using the provided routine in Java). Comment briefly on what you see. A test example with input x is classified as a 7 if the output g(W · x) of the final perceptron is greater than 0.5. Also show the results of testing your perceptron on a test set chosen as subset of the provided data (disjoint from the training set you use). Report the classification results for at least 5 different training set sizes. For each training set size, run at least 5 different experiments with a different random training set of the given size. Note that a “random” subset can be obtained using randperm in MATLAB, or by starting from a random index (Java or MATLAB). Plot % correct on test set versus # training examples on a graph by hand, in MATLAB, or using your favourite program. Part 2: Neural Networks Create a neural network that attempts to recognize all of the digits 0 through 9. There should be 10 output units, one corresponding to each of the 10 digits. The rest of the structure of the network is up to you. There should be at least 1 hidden layer of nodes in between the input and output layers. The input layer does not have to be all 784 input pixels (plus a bias term), it can be something else of your choosing. Train this network using back-propagation (see lecture slides). Again, train using some subset of the 60000 images, and use a disjoint subset to test your trained network. Again, show recognition rates on using at least 2 different sizes of training set (one run for each is sufficient this time). I will use a completely separate set of images to test your networks for the digit recognition contest. For the contest: 1. If you are using Java, please create a class RecognizeDigits XX YY, with your student numbers in place of XX and YY, as before. This class should extend the template class RecognizeDigits provided. 2. If you are using MATLAB, please create a function recognizeDigits XX YY, with your student numbers in place of XX and YY as before. Use the template provided without changing the function header. In short, your function/class should work with the run tournament file provided, with absolutely no modifications. Submitting Your Assignment You must create your assignment in electronic form. For each part of the assignment, submit the source code as well as the test output mentioned in each question. For part 2 give a brief summary of the structure of the network used, and any other design choices made. Submit these in one of the formats listed below. In total, you should submit: • All source code for parts 1 and 2 • Error rate plot for training perceptron • Visualization of learned weights for perceptron for one of these training sets, with brief comments • Error rates (don’t have to plot) for training neural network with ≥ 2 sizes of training set • Brief summary of structure of neural network and inputs The accepted text formats are: • ASCII Text • HTML • PDF (Portable Document Format) And the accepted image formats are: • GIF • JPEG • PDF You must include a completed cover sheet along with all the files from your completed assignment. This file is available from the course main page: http://www.cs.sfu.ca/ ~mori/courses/cmpt310/a5/cover_sheet_a5.txt This file will be used by the TA to give you feedback on your assignment, so don’t forget to complete it. This cover sheet also includes the grading scheme. All files should all be labeled appropriately so that the markers can easily follow and find your work. Create an archive (either *.zip or *.tar.gz) containing all relevant assignment files, plus the cover sheet. When you are done, go to the Assignment Submission Page at https://submit.cs.sfu.ca/ and follow the instructions there. [Less]

olpc-dhw

The goal of this project is to implement educational program for teaching handwriting on tablet PCs or touchscreen devices. It should help children learn the shapes of letters and improve their fine motorics, which is a different and not widely known task than handwriting recognition. The ... [More] application should be usable either as a practice and learning tool for children (with or without direct teacher's supervision) or as an analytical tool for teachers. It should help the child by providing animated tutorials with spoken descriptions talking and guessing possible problems (wrong pressure, bad shape/direction). The application should also help the teacher to focus on identified problems and compare them with historical data for the student. The application will consist of several modules: practices, like animated demonstrations accompanied by spoken description or tracing a template; teacher's tools such as editor and analyzer. Letters written by a student will be analyzed and stored in a database for future teacher's work. [Less]

zeez

This is a porting version of Zinnia(Version 0.05) in Actionscript which is open source for online handwriting recognition. Zinnia is based on Support Vector Machines which has learning and recognizing features, I only ported recognition part. So you can training data using Zinnia for develop ... [More] better results. Engine quite fast and good but it requires good trained model. Of course, you can use Zinnia-Tomoe model for Japanese and Chinese character recognition but model files are over 15 MB even if it's zipped so better use zinnia on server side for full character recognition. http://zinnia.sourceforge.net I'm using lots of Vectors and Flash 10's features, so it only supports from the version 10 of flash player. External library being used: Fzip as3flexunitlib --------- updates 2009 09 28 ---------- Now it uses the freeman chain algorithm to simplify strokes of a character. It's useful for increase accuracy because users' stroke points are more similar to the studied model data. Also I added Capital letter of English characters, although some of characters like B, W, require more training data. [Less]

kanjiteacher

This project uses state of the art Chinese/Japanese handwriting recognition methods in order to provide an Kanji teaching application with an error correction. Conceptually, the application is an e-learning environment for Japanese characters, intended for the foreign learner of the Japanese ... [More] language. In order to provide more than a multiple choice method, like most other systems, the application contains a handwriting recognition engine that can be used preferably with a handheld device like a PDA, but generally any stylus input device. The handwriting recognition method used is similar to the one proposed by Chen, J.-W. and S.-Y. Lee (1996) in their article "A Hierarchical Representation for the Reference Database of On-Line Chinese Character Recognition" in "Advances in Structural and Syntactical Pattern Recognition", Volume 1121 of "Lecture Notes in Computer Science", pp. 351--360. Berlin/Heidelberg, Germany: Springer. Nakagawa, M., J. Tokuno, B. et al. (2008) report their "Recent Results of Online Japanese Handwriting Recognition and Its Applications" in D. Doermann and S. Jaeger (Eds.) "Arabic and Chinese Handwriting Recognition", Volume 4768 of "Lecture Notes in Computer Science", pp. 170--195. Berlin/Heidelberg, Germany: Springer. The latter article gives important insights into character modeling, which are employed in this application. [Less]