University Homepage School Homepage School Contacts School Search

MLP 2017-18  |  News Archive  |  Lectures  |  Labs  |  Group Project  |  Coursework  |  Feedback  |  Computing  |  Piazza  |  Github

Machine Learning Practical (MLP) 2017-18

News

• Coursework 4 description
• Coursework 3 deadline extended to 16:00 on Monday 19 February
• Computing information - collected information and links on the MLP GPU cluster; see also slides on the GPU cluster.
• Information on, and basic code for, GPU computing and TensorFlow in branch 2017-8/semester_2_materials of the MLP github.
• Helpdesk each day (Monday-Friday), 2-3pm, in AT-5.08
• Coursework 3 description
• Semester 2 group projects
• News Archive

Overview

The Machine Learning Practical (MLP) for 2017-18 will be is concerned with deep neural networks. Doing this course involves the following:

• Implementing deep learning systems using python;
• Training and evaluating on data sets for tasks such as handwriting recognition;
• Designing and running machine learning experiments to investigate research questions;
• Reporting on your experiments, discussing and interpreting the results.

During semester 1 we shall focus on the classification of handwritten digits using the well-known MNIST dataset. Using a Python software framework that we shall provide, and a series of Jupyter notebooks, the aim of the course is to train multi-layer neural neural network classifiers and convolutional network classifiers to address this handwritten digit classification problem. There will be a series of ten weekly lectures in semester 1 to provide the required theoretical support to the practical work.

Semester 2 will be project-based, with a focus on using deep neural networks within the context of a group project, typically using TensorFlow (or another deep learning toolkit). The lectures will support the coursework, and also provide insights to the current state of the art in this very fast moving area, through some guest lectures.

Required background

The MLP course requires mathematical ability (calculus, linear algebra, and probability) and programming ability (the course will be based on Python using Numpy and TensorFlow). Some previous experience of machine learning is is extremely helpful.
Undergraduates: If you have taken Informatics 2B and IAML, and can program, you are qualified to do the course.
It is also recommended to take MLPR.

Details

• People
  • Lecturers:
  • Teaching assistant: Antreas Antoniou
  • Demonstrators (semester 1): Todor Davchev, Patric Fulop, Xinnuo Xu
  • Tutors (semester 2): Pavlos Andreadis, Antreas Antoniou, Todor Davchev, Joachim Fainberg, Patric Fulop, Miguel Jaques, Ben Krause, Boris Mocialov, Tanmoy Mukhejree, Steve Renals, Lazar Valkov, Xinnuo Xu, Chaoyun Zhang
  • Helpdesk (semester 2): Antreas Antoniou, Todor Davchev
• Locations (semester 2)
  • Lectures on Wednesdays 11:00, George Square Theatre. This room is large enough for all enrolled students to attend the same lecture!
  • Helpdesk each day (Monday-Friday), 2-3pm, in AT-5.08
  • Tutorial sessions as scheduled.
• Locations (semester 1)
  • Lectures: Wednesdays, 11:00, David Hume Lecture Theatre B OR Mondays, 09:00, Appleton Tower Lecture Theatre 4.
  • Labs: A number of weekly lab sessions will be scheduled in semester 1, students are expected to attend one of these.
    
  • "Office" hours in the Appleton Tower cafe (Absorb, on the concourse in front of the lecture theatres):
    • Mondays 10am (after the 9am lecture)
    • Wednesdays 10am (before the 11am lecture)
    If you have a question about the course, then you are welcome to come along and ask/discuss. If your question is about the software, the environment, or implementation issues relating to the labs or coursework, then please ask your questions in the lab, rather than the office hour.
• Official course pages
  • DRPS
  • Informatics course catalogue
• MLP course Q&A on Piazza
• Information on auditing the class, or taking it not for credit.
• Course web pages for last year (2016-17).

---

Copyright (c) University of Edinburgh 2015-2018
The MLP course material is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License
licence.txt
The software at https://github.com/CSTR-Edinburgh/mlpractical is licensed under the Modified BSD License.
This page maintained by Steve Renals.
Last updated: 2018/08/14 13:06:34UTC