How to use Deep Learning for Marketing?

(offered only once)

Deep Learning Deep Learning

„Deep-learning will transform every single industry.”

Andrew Ng


Abstract:
Deep Learning had a significant impact on many domains. This also applies to marketing. Consequently, this seminar has two parts. In a first part, we discuss the statistical foundations of deep learning. In a second part, you will work in a group on setting up your own deep learning model.

Instructors:
Dr. Markus Meierer
Luca Gaegauf

Type:
Seminar

Target audience:
Master students, assigned to “Wahlpflichtbereich BWL 4”.

Frequency:
irregular

APS/ECTS-points:
3

Work load statement:

Part Workload Total Time

Building up theoretical foundations/
Multiple-Choice-Tests

2*17.5h

35h
Group work 45h 45h

Online exercises

10h 10h
Total   90h

Maximum number of students:
25

Language:
English

previous knowledge and literature:
Goodfellow, Ian, Yoshua Bengio, and Aaron Courville. Deep learning. MIT press, 2016
A non-technical introduction to Python (or equivalent knowledge)

A non-technical introduction to machine learning (or equivalent knowledge)

Grading:
The examination of the module is carried out online. Online examination supervision is possible. The assessment consists of:
- Multiple-Choice-Tests
- Online exercises (DataCamp)
- Online exercises (Kaggle) & written report

Dates:

Wednesdays, 16:00 - 18:00
- 24.02.2021
- 03.03.2021
- 10.03.2021
- 31.03.2021
- 14.04.2021
- 12.05.2021

Location: ONLINE See https://www.vorlesungen.unizh.ch

Access and Registration:
Please contact our website for enrolling and for current information. The number of participants is limited. Thus, to apply for the seminar, please send an email with a recent transcript of records to markus.meierer@uzh.ch. If you receive a positive confirmation, you are asked and allowed to officially book this seminar using the “Buchungstool”. Booking the seminar without a positive confirmation from our chair is not implying the right to attend the course. In this case the course will be grad-ed as failed.

Note:
The information in the syllabus supports the official information in the electronic university calendar (VVZ – Vorlesungsverzeichnis). In case of doubt, the official information at the VVZ is valid.