The three assignments are considered completed. In the future, following work on the selected final project may be added here, too.

For each question in each assignment, besides the coding part, I usually have a corresponding jupyter notebook to record my written answers. They main include more details (e.g. backpropagation derivation) and could be used as in complementary to the stanford solution files.

CS224n: Natural Language Processing with Deep Learning Winter quarter (January - March, 2017)

http://web.stanford.edu/class/cs224n/syllabus.html

If some equations do not show up correctly on github rendered notebooks (.ipynb files), please try nbviewer.

http://nbviewer.jupyter.org/github/zyxue/stanford-cs224n/tree/master/

This course used Python 2.7.

# Due to version constraints of cudnn 5, higher version of tensorflow than 1.2 may not work
pip install --upgrade https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow_gpu-0.12.1-cp27-none-linux_x86_64.whl