#!/usr/bin/env python
# coding: utf-8

# # COMPGI19/COMPM083 Overview
# content at [https://uclmr.github.io/stat-nlp-book](https://uclmr.github.io/stat-nlp-book), click on slides for *Course Logistics*

# ### COMPGI19, COMPM083 Details
# 
# - **Lecturer**: [Sebastian Riedel](http://www.riedelcastro.org/)
# - **Teaching Assistants**: [Matko Bošnjak](http://matko.info/), [George Spithourakis](http://geospith.github.io/), Johannes Welbl, Ivan Sanchez
# - Lectures:  
#     -  Wednesday 5 PM - 6:30 PM, Roberts Building G06 Sir Ambrose Fleming LT
#     -  Friday 2PM - 3:30PM, Anatomy G29 J Z Young LT
# - **Office Hours**: Friday 5PM - 6PM, 1ES, 504A

# ### Prerequisites  1
# 
# * **Python**: including classes and inheritance, difference between list and tuples, variable arguments, dictionaries etc.
# * **Probabilities**: understand Bayes rule; what does marginalisation mean? What is conditioning? How to sample from a categorical distribution
# * **Math**: basic linear algebra, multi-dimensional calculus (differentiation ); understand what $argmax$ means

# ### Prerequisites  2
# 
# * **Jupyter Notebooks**: know how to create and run notebooks
# * **Command line tools**: know how to use a command line tools, `ssh`, `cd`, `mv`, `rm` etc.
# * **Git**: know how to use `git` (`clone`, `merge`, `pull` etc.)
# * **Installation**: be able to install docker on your machine, or be comfortable running a VM on the cloud (Azure)

# ### Enrolment
# 
# * Moodle: https://moodle.ucl.ac.uk/course/view.php?id=23928
# * Enrolment key: ???

# ### Expectations
# * I am not a *linguist*
#   * I probably don’t know your favourite linguistic framework or terminology
# * I am not a *cognitive scientist*
#   * I don’t know how humans process language
# * This course has no exams!
#   * You should learn how to construct stat NLP systems

# ### Course Material
# * We will be using the [stat-nlp-book](../overview.ipynb) project. 
# * Contains **interactive** [jupyter](http://jupyter.org/) notes and slides
#     * View statically [here](http://nbviewer.jupyter.org/github/uclmr/stat-nlp-book/blob/python/overview.ipynb)
#     * Use interactively via install, see [github repo](https://github.com/uclmr/stat-nlp-book) instructions  
# * References to other material are given in context.
# * This is work in progress.
#     * Use `git pull` regularly for updates
#     * *Watch* for updates, *star* if you like it
# * Please contribute by adding issues on github when you see errors.

# ### Lecture Preparation
# * Go through lecture notes, play with code
# * Do exercises
# * Read Background Material
# 

# ### Docker
# 
# * The book, tutorials and assignments run in a [docker](https://www.docker.com/) container
# * Container comes with all dependencies pre-installed
# * You can install it on your machine and Azure/AWS machines
# * We provide no support for non-docker installations

# ### Python
# 
# * Lectures, lab exercises and assignments focus on **Python** (version 3.6)
# * Python is a leading language for data science, machine learning etc., with many relevant libraries
# * We expect you to know Python, or be willing to learn it **on your own**
# * Labs and assignments focus on development within [jupyter notebooks](http://jupyter.org/)

# ### Discussion Forum
# 
# * Our moodle page has a **discussion forum**.
# * Please post questions there (instead of private emails) 
# * We give low priority to **questions already answered** in previous lectures, tutorials and posts, 
#     * and to **pure programming related issues**
# * We expect you to **online-search** for answers before.
# * You are highly encouraged to participate and **help each other** on the forum. 

# ### UCL-Machine Reading
# 
# * Research Group at UCL teaching machines to read
# * Webpage: http://mr.cs.ucl.ac.uk/ 
# * Twitter: 
#     * @uclmr https://twitter.com/uclmr
#     * @riedelcastro https://twitter.com/riedelcastro
# * Always looking for strong MSc and PhD students!