User:Sudeepam: Difference between revisions

::''My special focus would be to have a minimal trade-off between the accuracy and speed of the feature.'' Please take a look at the last, and additional section of 'Project Description'[https://wiki.octave.org/User:Sudeepam#Project_Description] for technical details. Please consider reading the Project Description section before going through the tentative timeline which is given below. I would like to apologize for creating this extra part but it describes some of the important technicalities of this project and I believed that they should be present here.

::-Persuade the community to use our data extraction script and help us collect training data. This will be done by discussing the benefits of a command line suggestion feature and sharing my rough, small scale implementation[https://github.com/Sudeepam97/Did_You_Mean] of this feature.

::-Ask the community to report issues with the m-scripts containing the current implementation. I’ll shift the current implementation to mercurial if required.

::-Discuss how we should receive the data generated by the users, work on the approach, and start the collection of data.

::-Organize the data as it is received and divide it to create proper, training, cross-validation, and test sets.

::'''Week 2 and Week 3 (May, 21 – June, 3):''' Most of the code of the Neural Network would be identical to my current implementation and so I’ll start by making my current implementation bug free (Some known issues can be found here: [https://github.com/Sudeepam97/Did_You_Mean/issues]) and by coding it according to the Octave coding standards. I plan to keep the user data coming for these weeks also and so I’ll leave room for network parameters such as the number of hidden layers and the number of neurons per hidden layer because these are data dependent parameters. If all this work gets completed before the expected time, I’ll automatically move on to complete next week’s work.

::'''Week 4 (June, 4 – June, 10):''' By now we will have sufficient data, this will include the data received from octave-online.net ''(please see the project description section)'' and from approximately 6 weeks of extraction script’s usage. I’ll quickly give a final look to the data and start training the Neural Network with it. I will choose appropriate values of the data dependent network parameters which, while keeping the speed of the Neural Network fast, would fit the learning parameters (weights) of the Neural Network to our data with a high level of accuracy. I would then measure the accuracy of the Network on cross validation and test sets and see how our network generalizes to unknown typographic errors. I will also write some additional tests for the set of m-scripts used.

::'''Phase 1 evaluations goal:''' A set of working neural network m-scripts, which could suggest corrections for typographic errors.