Big Data Management and Analytics 2018

In almost all areas of business, industry, science, and everybody's life, the amount of available data that contains value and knowledge is immense and fast growing. However, turning data into information, information into knowledge, and knowledge into value is challenging.To extract the knowledge, the data needs to be stored, managed, and analyzed. Thereby, we not only have to cope with increasing amount of data, but also with increasing velocity, i.e., data streamed in high rates, with heterogeneous data sources and also more and more have to take data quality and reliability of data and information into account. These properties referring to the four V's (Volume, Velocity, Variety, and Veracity) are the key properties of "Big Data". Big Data grows faster than our ability to process the data, so we need new architectures, algorithms and approaches for managing, processing, and analyzing Big Data that goes beyond traditional concepts for knowledge discovery and data mining. This course introduces Big Data, challenges associated with Big Data, and basic concepts for Big Data Management and Big Data Analytics which are important components in the new and popular field Data Science.


Practicum "Human Computation and Analytics"

The course content is currently available here.

Graphical Models & Causal Reasoning

Graphical models provide a general framework for describing statistical relations between random variables and performing inference. More recently, they have become a popular framework for reasoning about causal relations. Graphical models are employed in a wide range of applications, from modelling gene regulatory networks to studying interactions in social groups. In this seminar, we will introduce the basics of inference in graphical models, discuss how they can be employed to perform causal inference, study causal reasoning in directed acyclic graphs (DAGs), and critically examine recent theoretical advances and real-world applications.

Brain-Computer Interfaces

Brain-Computer Interfaces (BCIs) are systems that employ machine learning methods to decode subjects’ intentions from brain imaging data. They hold the promise of enabling severely paralyzed patients to communicate and interact with their environment. In this seminar, we will take a look at the history of BCIs, introduce the design of invasive and non-invasive BCIs, study machine learning methods for decoding mental states from brain imaging data, and discuss the open problems that need to be solved to move BCIs from the lab into the real world.

[s18] Predictive Modelling (Grosse-Wentrup / Scheipl)

Outline

The lecture deals with theoretical and practical concepts from the fields of statistical learning and machine learning. The main focus is on predictive modeling. The tutorial applies these concepts and methods to real examples for illustration purposes.

Class meets twice per week in the building at Schellingstr. 3: 

Mondays from 10–12 in R055, and Wednesdays from 12–14 in S007

Semester Plan:
  # 
  Date 
  Day 
                               Topic                             
01     09.4.    
   Mon.   
Intro.  (F)
02 11.4.
 Wed.
 Learning Theory  (M)
03 16.4.
 Mon.
 Exercise 1  (A)
04 18.4.
 Wed.
 Learning Theory  (M)
05 23.4.
 Mon.
 CART  (F)
06 25.4.
 Wed.
 RF  (F)
07 30.4.
 Mon.
 Exercise 2  (A)
08 02.5.
 Wed.
 TBA  (M)
09 07.5.
 Mon.
 Learning Theory  (F)
10 09.5.
 Wed.
 TBA  (M)
11 14.5.
 Mon.
 Exercise 3  (A)
12 16.5.
 Wed.
 Performance Estimation & Resampling  (F)
-- 21.5.
 Mon.
 holiday
13 23.5.
 Wed.
 Boosting a  (F)
14 28.5.
 Mon.
 Exercise 4  (A)
15 30.5.
 Wed.
 Boosting b  (F)
16 04.6.
 Mon.
 ROC  (F)
17 06.6.
 Wed.
 TBA  (M)
18 11.6.
 Mon.
 TBA  (M)
19
 13.6.
 Wed.
 Exercise 5  (A)
20 18.6.
 Mon.
 GPs / Tuning / MBO  (F)
-- 20.6.
 Wed.
 cancelled
21 25.6.
 Mon.
 Exercises 6  (A)
22 27.6.
  Wed. Variable / Feature Selection  (F)
23
 02.7. Mon.
 Exercises 7 / Q & A  (A)
 24  04.7.  Wed.  Q & A

Statistical Reasoning and Inference II (Sampling and Experimental Design)