data.stage festival.stage tech.stage work.shop(0) work.shop(1)
08:00
Doors Open
08:00 - 09:00
08:15
08:30
08:45
09:00
09:15
09:30
Coffee Break
09:30 - 09:45
Coffee Break
09:30 - 09:45
Coffee Break
09:30 - 09:45
Coffee Break
09:30 - 09:45
Coffee Break
09:30 - 09:45
09:45
Energy.AI or how to decarbonize, decentralize and digitize our energy
Dr. Juan Bernabé Moreno (E.ON Digital Technology GmbH)
09:45 - 10:15
Energy.AI or how to decarbonize, decentralize and digitize our energyThe energy companies are indisputable players in shaping a sustainable tomorrow...
AdsISee: Advertisement Detection for Sponsorship Evaluation in Sport Events
Dr. Andreas Weiler (Zurich University of Applied Sciences School of Engineering)
09:45 - 10:15
AdsISee: Advertisement Detection for Sponsorship Evaluation in Sport EventsIn this work, we present AdsISee, a real-life application for the detection and tracking of advertisements in broadcasts of sport events for supporting business analysts in the task of sponsorship evaluation and reporting.
Mobile Asset Tracking - Data Based Quality Insurance
Veenet Muthraja (Munich Re)
09:45 - 10:15
Mobile Asset Tracking - Data Based Quality InsuranceLogistics - current Situation Cargo logistics are complex and highly non-transparent While the goods are shipped there is no transparency on: Status of shipment Estimated time of arrival Location of cargo Quality of shipment....
10:00
10:15
Psychographic User Segmentation Based Model to Overcome One-Size-Fits-All
Marc Roulet (XING GmbH & Co. KG), Michael Horn (XING GmbH & Co. KG)
10:15 - 10:45
Psychographic User Segmentation Based Model to Overcome One-Size-Fits-AllXING has a vast data pool of user activity of their 16 million registered users and their activity on the site, but as many other companies struggles to extract the desired value out of the large available dataset. In this project XING used a three step approach to increase relevance of its content across marketing and product development...
10:30
10:45
Cooking made smarter through Data - Data Architecture at Vorwerk
Marcel Hellmann (Vorwerk International & Co. KmG), David Sterz (Mindcurv GmbH)
10:45 - 11:15
Cooking made smarter through Data - Data Architecture at VorwerkThe Thermomix TM5 and TM6 from Vorwerk are among the most successful and most advanced smart kitchen appliances globally. Together with the recipe platform Cookidoo they form a digital ecosystem at the heart of the digitized kitchen...
Poster-Pitch-Session
Our #PosterPitchSpeakers have taken up the task to perform on stage! They will each get 3 minutes and 3 slides to pitch their use case / story one after the other.
10:45 - 11:15
11:00
11:15
Coffee Break
11:15 - 11:45
Coffee Break
11:15 - 11:45
Coffee Break
11:15 - 11:45
Coffee Break
11:15 - 11:45
Coffee Break
11:15 - 11:45
11:30
11:45
Digital Chemist: Reinforcement Learning for Inverse Molecular DesignInverse molecular design is the process of optimizing a target molecule given a number of physical properties. Given the advent of modern reinforcement learning it is now possible to train agents to solve this tasks and supporting chemist in their daily work.
The Beltracchi Code - the forger of the century has misled dozens of (human) expertsPainter classification is a well-known research field in academic AI. The project presented here not only predicts artists with an accuracy of more than 90 percent but also levels out huge class imbalances. The main is to detect fake or counterfeit images. Two approaches are pursued. Firstly, 160 images from the “century-counterfeiter” Wolfgan
Meet the Poster-Pitch-Speakers
Our #PosterPitchSpeakers have taken up the task to perform for you! They will each get 3 minutes to pitch their use case / story one after the other.
11:45 - 12:45
12:00
12:15
AI Kickstart - from Hype to operationalisation within a few months
Jens Hütter (Ströer SE & Co. KGaA)
12:15 - 12:45
AI Kickstart - from Hype to operationalisation within a few monthsStröer is the biggest billboard and online advertiser in Germany. We are coming from a business with long history and want to share our learnings in AI and Automatisation with other companies. In our presentation we will explain how we managed to have a long-term strategy in IT while having a business that demands quick results! We will showcase how we developed AI Solutions with the help of our partners and how we try to manage the necessary change in working habits and infrastructure...
Finding image duplicates with 'imagededup' python package!
Tanuj Jain (Axel Springer Ideas Engineering GmbH)
12:15 - 12:45
Finding image duplicates with 'imagededup' python package!Finding duplicates in an image collection is a recurring task for many image-related machine learning use cases. For example, presence of duplicates can create extreme biases in the evaluation of your ML model. imagededup is a python package that simplifies the task of finding exact and near duplicates. This package provides functionality to make use of hashing algorithms that are particularly good at finding exact duplicates as well as convolutional neural networks which are also adept at finding near duplicates. An evaluation framework is also provided to judge the quality of deduplication for a given dataset. The talk takes the user through the package functionality.
12:30
12:45
Lunch Break
12:45 - 14:15
Lunch Break
12:45 - 14:15
Lunch Break
12:45 - 14:15
Lunch Break
12:45 - 14:15
13:00
13:15
13:30
13:45
14:00
14:15
Panel - How does Germany position itself across industries in the field of AI?
Alexander Thamm (Moderation), Marcel Kling, Holger Kömm, Dr. Alexander Borek
14:15 - 15:15
Lessons learned from automating regulatory processes with data and AI
Lukas Hestermeyer (Volkswagen Financial Services AG)
14:15 - 14:45
Lessons learned from automating regulatory processes with data and AIAutomating regulatory processes often require monitoring the model’s decision closely and supplying reasoning for them. Due to this and a general skepticism towards AI solutions, the data scientist’s choices are limited, and the project’s progress can slow down. In this talk, I will show why implementing data products in this realm still pays off, and how data collection is related to that.
14:30
14:45
Free slot
14:45 - 15:15
Customer Targeting with Uplift Modelling using Gradient Boosting at VerivoxVerivox is an online comparisor based in Heidelberg. One of our main products are \\\\\\\'Loans\\\\\\\'. Customers apply online for a loan and obtain immediately offers from different banks. Credit Advisory can then support our customers by figuring out the most suitable loan offer as well as motivating them to actually apply for the loan. A crucial point is the time when the customer is contacted. Speed and Conversion show a high positive correlation due to the competitive environment....
15:00
15:15
Weather-based forecasting: How to improve bakery sales planning using weatherOne of the key challenges of bakeries is offering the right product selection in every location on daily basis. Among quality and price, weather is also a key demand driver. Clearly, automated weather-based forecasting is crucial in order to reduce overstocking, which wastes food and money, and to avoid out-of-stock situations, which causes revenue losses. Dr. Stefan Bornemann, COO at wetter.com, will explain (i) which data and modelling techniques are used to create daily sales forecasts considering weather effects and (ii) which challenges occur when turning a proof of concept for one bakery to an automated cloud-forecast solution for hundreds of bakeries.
Free slot
15:15 - 15:45
Physicians in the loop: neuropathologists in the field of deep learning
Samir Jabari (Institute for Neuropathology, University Hospitals Erlangen), Joshua Kubach (Friedrich Alexander University Erlangen Nürnberg)
15:15 - 15:45
Physicians in the loop: neuropathologists in the field of deep learningNeuropathology remains a periphery in the field of digital medicine and especially deep learning. The use of automated assistance systems in neuropathological diagnostics is still pretty poorly developed or not even existent at all in the day to day work. Neuropathologists still look at tissue through microscopes. However, our research group enters the field of digital neuropathology from the side of physicians bringing pathogenetic, pathophysiologic and histologic insight to the table. Our goal is to base our work on intuitions and problems in routine neuropathologic work-up to enhance clinicopathologic decision making and research...
15:30
15:45
Beer Break
15:45 - 16:00
Beer Break
15:45 - 16:00
Beer Break
15:45 - 16:00

data.stage

festival.stage

tech.stage

work.shop(0)

work.shop(1)

  • Coffee Break
    09:30 - 09:45
  • Coffee Break
    11:15 - 11:45
data.stage festival.stage tech.stage work.shop(0) work.shop(1)
09:30
Coffee Break
09:30 - 09:45
Coffee Break
09:30 - 09:45
Coffee Break
09:30 - 09:45
Coffee Break
09:30 - 09:45
Coffee Break
09:30 - 09:45
09:45
10:00
10:15
10:30
10:45
11:00
11:15
Coffee Break
11:15 - 11:45
Coffee Break
11:15 - 11:45
Coffee Break
11:15 - 11:45
Coffee Break
11:15 - 11:45
Coffee Break
11:15 - 11:45
11:30
11:45
12:00
12:15
12:30
12:45
Lunch Break
12:45 - 14:15
Lunch Break
12:45 - 14:15
Lunch Break
12:45 - 14:15
Lunch Break
12:45 - 14:15
13:00
13:15
13:30
13:45
14:00
14:15
14:30
14:45
Free slot
14:45 - 15:15
15:00
15:15
Free slot
15:15 - 15:45
15:30
15:45
Beer Break
15:45 - 16:00
Beer Break
15:45 - 16:00
Beer Break
15:45 - 16:00

data.stage

  • Coffee Break
    09:30 - 09:45
  • Coffee Break
    11:15 - 11:45
  • Lunch Break
    12:45 - 14:15
  • 15:45 - 16:00

festival.stage

  • Coffee Break
    09:30 - 09:45
  • Coffee Break
    11:15 - 11:45
  • Lunch Break
    12:45 - 14:15
  • Free slot
    14:45 - 15:15
  • Free slot
    15:15 - 15:45
  • 15:45 - 16:00

tech.stage

  • Coffee Break
    09:30 - 09:45
  • Coffee Break
    11:15 - 11:45
  • Lunch Break
    12:45 - 14:15
  • 15:45 - 16:00

work.shop(0)

  • Coffee Break
    09:30 - 09:45
  • Coffee Break
    11:15 - 11:45
  • Lunch Break
    12:45 - 14:15

work.shop(1)

  • Coffee Break
    09:30 - 09:45
  • Coffee Break
    11:15 - 11:45
data.stage festival.stage tech.stage work.shop(0) work.shop(1)
08:00
Doors Open
08:00 - 09:00
08:15
08:30
08:45
09:00
09:15
09:30
Coffee Break
09:30 - 09:45
Coffee Break
09:30 - 09:45
Coffee Break
09:30 - 09:45
Coffee Break
09:30 - 09:45
Coffee Break
09:30 - 09:45
09:45
Energy.AI or how to decarbonize, decentralize and digitize our energy
Dr. Juan Bernabé Moreno (E.ON Digital Technology GmbH)
09:45 - 10:15
Energy.AI or how to decarbonize, decentralize and digitize our energyThe energy companies are indisputable players in shaping a sustainable tomorrow...
AdsISee: Advertisement Detection for Sponsorship Evaluation in Sport Events
Dr. Andreas Weiler (Zurich University of Applied Sciences School of Engineering)
09:45 - 10:15
AdsISee: Advertisement Detection for Sponsorship Evaluation in Sport EventsIn this work, we present AdsISee, a real-life application for the detection and tracking of advertisements in broadcasts of sport events for supporting business analysts in the task of sponsorship evaluation and reporting.
Mobile Asset Tracking - Data Based Quality Insurance
Veenet Muthraja (Munich Re)
09:45 - 10:15
Mobile Asset Tracking - Data Based Quality InsuranceLogistics - current Situation Cargo logistics are complex and highly non-transparent While the goods are shipped there is no transparency on: Status of shipment Estimated time of arrival Location of cargo Quality of shipment....
10:00
10:15
Psychographic User Segmentation Based Model to Overcome One-Size-Fits-All
Marc Roulet (XING GmbH & Co. KG), Michael Horn (XING GmbH & Co. KG)
10:15 - 10:45
Psychographic User Segmentation Based Model to Overcome One-Size-Fits-AllXING has a vast data pool of user activity of their 16 million registered users and their activity on the site, but as many other companies struggles to extract the desired value out of the large available dataset. In this project XING used a three step approach to increase relevance of its content across marketing and product development...
10:30
10:45
Cooking made smarter through Data - Data Architecture at Vorwerk
Marcel Hellmann (Vorwerk International & Co. KmG), David Sterz (Mindcurv GmbH)
10:45 - 11:15
Cooking made smarter through Data - Data Architecture at VorwerkThe Thermomix TM5 and TM6 from Vorwerk are among the most successful and most advanced smart kitchen appliances globally. Together with the recipe platform Cookidoo they form a digital ecosystem at the heart of the digitized kitchen...
Poster-Pitch-Session
Our #PosterPitchSpeakers have taken up the task to perform on stage! They will each get 3 minutes and 3 slides to pitch their use case / story one after the other.
10:45 - 11:15
11:00
11:15
Coffee Break
11:15 - 11:45
Coffee Break
11:15 - 11:45
Coffee Break
11:15 - 11:45
Coffee Break
11:15 - 11:45
Coffee Break
11:15 - 11:45
11:30
11:45
Digital Chemist: Reinforcement Learning for Inverse Molecular DesignInverse molecular design is the process of optimizing a target molecule given a number of physical properties. Given the advent of modern reinforcement learning it is now possible to train agents to solve this tasks and supporting chemist in their daily work.
The Beltracchi Code - the forger of the century has misled dozens of (human) expertsPainter classification is a well-known research field in academic AI. The project presented here not only predicts artists with an accuracy of more than 90 percent but also levels out huge class imbalances. The main is to detect fake or counterfeit images. Two approaches are pursued. Firstly, 160 images from the “century-counterfeiter” Wolfgan
Meet the Poster-Pitch-Speakers
Our #PosterPitchSpeakers have taken up the task to perform for you! They will each get 3 minutes to pitch their use case / story one after the other.
11:45 - 12:45
12:00
12:15
AI Kickstart - from Hype to operationalisation within a few months
Jens Hütter (Ströer SE & Co. KGaA)
12:15 - 12:45
AI Kickstart - from Hype to operationalisation within a few monthsStröer is the biggest billboard and online advertiser in Germany. We are coming from a business with long history and want to share our learnings in AI and Automatisation with other companies. In our presentation we will explain how we managed to have a long-term strategy in IT while having a business that demands quick results! We will showcase how we developed AI Solutions with the help of our partners and how we try to manage the necessary change in working habits and infrastructure...
Finding image duplicates with 'imagededup' python package!
Tanuj Jain (Axel Springer Ideas Engineering GmbH)
12:15 - 12:45
Finding image duplicates with 'imagededup' python package!Finding duplicates in an image collection is a recurring task for many image-related machine learning use cases. For example, presence of duplicates can create extreme biases in the evaluation of your ML model. imagededup is a python package that simplifies the task of finding exact and near duplicates. This package provides functionality to make use of hashing algorithms that are particularly good at finding exact duplicates as well as convolutional neural networks which are also adept at finding near duplicates. An evaluation framework is also provided to judge the quality of deduplication for a given dataset. The talk takes the user through the package functionality.
12:30
12:45
Lunch Break
12:45 - 14:15
Lunch Break
12:45 - 14:15
Lunch Break
12:45 - 14:15
Lunch Break
12:45 - 14:15
13:00
13:15
13:30
13:45
14:00
14:15
Panel - How does Germany position itself across industries in the field of AI?
Alexander Thamm (Moderation), Marcel Kling, Holger Kömm, Dr. Alexander Borek
14:15 - 15:15
Lessons learned from automating regulatory processes with data and AI
Lukas Hestermeyer (Volkswagen Financial Services AG)
14:15 - 14:45
Lessons learned from automating regulatory processes with data and AIAutomating regulatory processes often require monitoring the model’s decision closely and supplying reasoning for them. Due to this and a general skepticism towards AI solutions, the data scientist’s choices are limited, and the project’s progress can slow down. In this talk, I will show why implementing data products in this realm still pays off, and how data collection is related to that.
14:30
14:45
Free slot
14:45 - 15:15
Customer Targeting with Uplift Modelling using Gradient Boosting at VerivoxVerivox is an online comparisor based in Heidelberg. One of our main products are \\\\\\\'Loans\\\\\\\'. Customers apply online for a loan and obtain immediately offers from different banks. Credit Advisory can then support our customers by figuring out the most suitable loan offer as well as motivating them to actually apply for the loan. A crucial point is the time when the customer is contacted. Speed and Conversion show a high positive correlation due to the competitive environment....
15:00
15:15
Weather-based forecasting: How to improve bakery sales planning using weatherOne of the key challenges of bakeries is offering the right product selection in every location on daily basis. Among quality and price, weather is also a key demand driver. Clearly, automated weather-based forecasting is crucial in order to reduce overstocking, which wastes food and money, and to avoid out-of-stock situations, which causes revenue losses. Dr. Stefan Bornemann, COO at wetter.com, will explain (i) which data and modelling techniques are used to create daily sales forecasts considering weather effects and (ii) which challenges occur when turning a proof of concept for one bakery to an automated cloud-forecast solution for hundreds of bakeries.
Free slot
15:15 - 15:45
Physicians in the loop: neuropathologists in the field of deep learning
Samir Jabari (Institute for Neuropathology, University Hospitals Erlangen), Joshua Kubach (Friedrich Alexander University Erlangen Nürnberg)
15:15 - 15:45
Physicians in the loop: neuropathologists in the field of deep learningNeuropathology remains a periphery in the field of digital medicine and especially deep learning. The use of automated assistance systems in neuropathological diagnostics is still pretty poorly developed or not even existent at all in the day to day work. Neuropathologists still look at tissue through microscopes. However, our research group enters the field of digital neuropathology from the side of physicians bringing pathogenetic, pathophysiologic and histologic insight to the table. Our goal is to base our work on intuitions and problems in routine neuropathologic work-up to enhance clinicopathologic decision making and research...
15:30
15:45
Beer Break
15:45 - 16:00
Beer Break
15:45 - 16:00
Beer Break
15:45 - 16:00

data.stage

festival.stage

tech.stage

work.shop(0)

work.shop(1)

  • Coffee Break
    09:30 - 09:45
  • Coffee Break
    11:15 - 11:45
No events available!