<html><head><meta http-equiv="Content-Type" content="text/html charset=us-ascii"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class=""><div class="">Thanks for getting in touch and welcome!</div><div class=""><br class=""></div><div class=""></div><blockquote type="cite" class=""><div class="">I have great interests in contributing to the FastML code base, particularly in</div><div class="">extending or improving deep learning modules within FastML. In particular, I</div><div class="">would like to implement GRUs and augment the current implementation of LSTMs to</div><div class="">include peephole connections which have become very popular.</div></blockquote><div class=""><br class=""></div><div class="">It would be great to see more deep learning modules, that said I would really</div><div class="">like to see a GRU implementation in the future. The LSTM layer already includes</div><div class="">an implementation of peephole connections.</div><div class=""><br class=""></div><div class=""></div><blockquote type="cite" class=""><div class="">I would also like to implement the CBOW and the word2vec models for FastML as</div><div class="">they have also become quite popular in the NLP community.</div></blockquote><div class=""><br class=""></div><div class="">I think it doesn't make much sense to pick various methods an implement them,</div><div class="">without providing a model to use them. On the other side, I'm not sure that the</div><div class="">project is enough work for 3 months, in which you are expected to work full-time.</div><div class="">However, If you want to continue down that path, maybe we can</div><div class="">find something that fits better with the codebase.</div><div class=""><br class=""></div><div class="">I hope this is helpful, let me know if I can clarify anything.</div><div class=""><br class=""></div><div class="">Thanks, Marcus</div><div class=""><br class=""></div><div><blockquote type="cite" class=""><div class="">On 13 Mar 2016, at 07:04, Shikhar Murty <<a href="mailto:shikhar.murty@gmail.com" class="">shikhar.murty@gmail.com</a>> wrote:</div><br class="Apple-interchange-newline"><div class=""><div dir="ltr" class="">Apologies, but I seem to have confused FastML for mlpack for some reason, due to the similar looking names. However, I meant mlpack.<div class=""><br class=""></div><div class=""><br class=""></div></div><div class="gmail_extra"><br class=""><div class="gmail_quote">On Sun, Mar 13, 2016 at 11:06 AM, Shikhar Murty <span dir="ltr" class=""><<a href="mailto:shikhar.murty@gmail.com" target="_blank" class="">shikhar.murty@gmail.com</a>></span> wrote:<br class=""><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr" class="">Hi Marcus,<div class=""><br class=""></div><div class=""><div style="margin:0px;padding:0px;border:0px;font-family:Arial,Helvetica,sans-serif;font-size:13px" class="">I'm a junior year EE undergrad (with elective concentration in CS) at IIT, Delhi. I'm an undergraduate researcher in Deep learning and NLP. I have implemented a bunch of ANNs and recently have started using FastML. I have familiarised myself with the code base of FastML, and understand the ANN implementation and the RNN implementation along with the optimisers module. I'm quite keen on participating in GSOC'16 under FastML, and request you to mentor me for the same.</div><div style="margin:0px;padding:0px;border:0px;font-family:Arial,Helvetica,sans-serif;font-size:13px" class=""><br class=""></div><div style="margin:0px;padding:0px;border:0px;font-family:Arial,Helvetica,sans-serif;font-size:13px" class="">As an undergraduate researcher, I've read and understood multiple papers in Deep learning, for instance Collobert et al (NLP from scratch), Mikolov et al. (word2vec), Dropouts, Adam, Bengio's paper on neural network language models and so on.</div><div style="margin:0px;padding:0px;border:0px;font-family:Arial,Helvetica,sans-serif;font-size:13px" class=""><br class=""></div><div style="margin:0px;padding:0px;border:0px;font-family:Arial,Helvetica,sans-serif;font-size:13px" class="">I have great interests in contributing to the FastML code base, particularly in extending or improving deep learning modules within FastML. In particular, I would like to implement GRUs and augment the current implementation of LSTMs to include peephole connections which have become very popular. I would also like to implement the CBOW and the word2vec models for FastML as they have also become quite popular in the NLP community. </div><div style="margin:0px;padding:0px;border:0px;font-family:Arial,Helvetica,sans-serif;font-size:13px" class=""><br class=""></div><div style="margin:0px;padding:0px;border:0px;font-family:Arial,Helvetica,sans-serif;font-size:13px" class="">Could you please give me some pointers on how I should structure my application for GSOC to boost my chances? </div><div style="margin:0px;padding:0px;border:0px;font-family:Arial,Helvetica,sans-serif;font-size:13px" class=""><br class=""></div><div style="margin:0px;padding:0px;border:0px;font-family:Arial,Helvetica,sans-serif;font-size:13px" class="">Thank you for your time and I look forward to a positive response</div><div style="margin:0px;padding:0px;border:0px;font-family:Arial,Helvetica,sans-serif;font-size:13px" class=""><br class=""></div><div style="margin:0px;padding:0px;border:0px;font-family:Arial,Helvetica,sans-serif;font-size:13px" class="">Regards,</div></div><div style="margin:0px;padding:0px;border:0px;font-family:Arial,Helvetica,sans-serif;font-size:13px" class=""><br class="">Shikhar Murty</div></div>
</blockquote></div><br class=""></div>
</div></blockquote></div><br class=""></body></html>