05/05 - 30/05 (community bonding period)

Week 1 Begin to stay in contact and familiarize with the community, using both the mailing list and the IRC channel. Improve expertise with tools like Mercurial and autotools. Install and run Pytave [3] Read Matlab doc of Neural Network Toolbox [2] classes and basic functions, with a focus on the deep learning part about CNNs.

Week 2 Test Pytave and figure out if there are some bugs or missing features in the specific part that we need to use. Figure out if we need some object programming in Octave (like classdef) and test it.

Week 3 Deeply analyze Python Tensorflow APIs [3] and read Stanford tutorial "Tensorflow for Deep Learning Research" [4]. 

30/05 - 30/06 (Phase 1)

Week 4,5 Work on the makefile in order to link TF in Python and test some basic nets with TF.

Week 6,7 Write all the Octave classes for every layer. Because of the focus on Matlab Nnet Toolbox, we will start to define the fundamental layers used for CNNs : Convolutional layer, ReLU layer, Normalization layer, Average pooling layer object, Max pooling layer, Fully connected layer, Dropout layer, Softmax layer, Classification output layer, Regression output layer.

Week 8 Complete all the remaining tasks before thePhase 1” evaluation. Implement a draft of the training functions (seriesNetwork object, trainNetwork, trainingOptions) without all options and parameters.

01/07 - 28/07 (Phase 2)

Week 9-10 Implement a complete working version of seriesNetwork (including definition of methods like activations, classify and predict).

Week 11 Implement a complete working version of trainNetwork.

Week 12 Implement a complete working version of trainingOptions. Complete all the remaining tasks before thePhase 2” evaluation.

28/07 - 25/08 (Final phase)

Week 13 Able the parallelization and analyze CUDA integration [5].

Week 14 Implementation of a cool application like deepDreamImage [6] and (if some time is left) more advanced nets like (AlexNet, vgg16, vgg19).

Week 15-16 Complete all the remaining tasks and finalize the documentation.


Popular posts from this blog

Introductory Post

Package structure