Deep Learning for Natural Language Processing - 10th Meetup

The 10th meeting of our CS224d: Deep Learning for Natural Language Processing (http://cs224d.stanford.edu/) series will be Thursday 1/26/2017 from 6-8 pm.

------------------------------------------------------------

We will meet again at Comcast, and we thank them again for their continued support. Their building doors close at 6 pm, but there will be a Comcast employee at the entrance until 6:15 pm. Please bring your photo ID. If this is your first time attending and your Meetup name doesn't match your ID, please send us your ID name, so that we can add it to the attendee list that Comcast requires.

------------------------------------------------------------

About this meeting:

Our previous meeting was lab only; we worked on Problem Set 2, "Deep and Recurrent Neural Networks," going through the solutions to Problems 1(a)-1(e), 2(a), 2(b) and 3(a). We'll start this meeting with Dmitrijs Milajevs' review of his ipython notebook, https://github.com/dimazest/tf-intro/blob/master/01-intro.ipynb , which records his initial experiments with TensorFlow (https://www.tensorflow.org/) and deep learning, and goes into tensorboard and queues. Thank you, Dmitrijs, for sharing this material and offering to walk us through it!

We'll continue the meeting by getting back to the next lecture of the 2016 course CS224d: Deep Learning for Natural Language Processing (http://cs224d.stanford.edu/). The file containing the slides for that lecture is css224d-lecture9.pdf (http://cs224d.stanford.edu/lectures/CS224d-Lecture9.pdf) (note that the file's title slide says, "Lecture 8: Recap, Projects and Fancy Recurrent Neural Networks for Machine Translation", and lecture is listed in the course syllabus (http://cs224d.stanford.edu/syllabus.html) for 4/26 as "GRUs & LSTMS - for machine translation"). The material for this lecture is also covered in Lecture Notes 4 (http://cs224d.stanford.edu/lecture_notes/notes4.pdf).

The video for this 2016 lecture is missing, but the outline in the slides matches this video (http://dsg.rushter.com/video/320/) from the 2015 version of the course. Please view this video before the meetup.

------------------------------------------------------------

We are continuing to add content to our shared GitHub repository (https://github.com/dcdlwg/stanford_cs224d) at DC DLWG (https://github.com/dcdlwg). The solutions to problems we've gone over in our meetings have been uploaded to the repo, and we will continue to share resources and code there as we progress through the course. You can share your own work by creating your own repo at DC DLWG (https://github.com/dcdlwg). So please create a GitHub account when you get a chance, if you don’t have one already.

We try to accommodate all levels of experience but the course we are following assumes familiarity with the following: Proficiency in Python, calculus, linear algebra, basic probability and statistics and some concepts of machine learning. Please look through the course website (http://cs224d.stanford.edu/) to see if this is the right level for you.