no code implementations • 15 Apr 2024 • Johannes Schneider
To this end, we focus on surveying existing works.
no code implementations • 5 Feb 2024 • Johannes Schneider, Rene Abraham, Christian Meske
Generative Artificial Intelligence (GenAI), specifically large language models like ChatGPT, has swiftly entered organizations without adequate governance, posing both opportunities and risks.
no code implementations • 11 Dec 2023 • Johannes Schneider, Mohit Prabhushankar
The learning dynamics of deep neural networks are not well understood.
no code implementations • 26 Nov 2023 • Johannes Schneider, Steffi Haag, Leona Chandra Kruse
Large language models LLMs like ChatGPT have reached the 100 Mio user barrier in record time and might increasingly enter all areas of our life leading to a diverse set of interactions between those Artificial Intelligence models and humans.
no code implementations • 30 Oct 2023 • Luca Longo, Mario Brcic, Federico Cabitza, Jaesik Choi, Roberto Confalonieri, Javier Del Ser, Riccardo Guidotti, Yoichi Hayashi, Francisco Herrera, Andreas Holzinger, Richard Jiang, Hassan Khosravi, Freddy Lecue, Gianclaudio Malgieri, Andrés Páez, Wojciech Samek, Johannes Schneider, Timo Speith, Simone Stumpf
As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
no code implementations • 5 Oct 2023 • Johannes Schneider
Neural networks are not learning optimal decision boundaries.
no code implementations • 9 Sep 2023 • Johannes Schneider, Bernd Schenk, Christina Niklaus, Michaelis Vlachos
Thus, in this manuscript we provide an evaluation of a large language model for the purpose of autograding, while also highlighting how LLMs can support educators in validating their grading procedures.
1 code implementation • 23 Jul 2023 • Alfred Sopi, Johannes Schneider, Jan vom Brocke
Non-fungible tokens(NFTs) are on the rise.
1 code implementation • 30 Apr 2023 • Giovanni Apruzzese, Pavel Laskov, Johannes Schneider
Unfortunately, the value of ML for NID depends on a plethora of factors, such as hardware, that are often neglected in scientific literature.
1 code implementation • 6 Feb 2023 • Johannes Schneider
Pre-trained language models have led to a new state-of-the-art in many NLP tasks.
no code implementations • 1 Feb 2023 • Johannes Schneider, Michalis Vlachos
Deep learning has made tremendous progress in the last decade.
no code implementations • 17 Dec 2022 • Johannes Schneider
Foundation models can be disruptive for future AI development by scaling up deep learning in terms of model size and training data's breadth and size.
no code implementations • 18 Mar 2022 • Johannes Schneider, Giovanni Apruzzese
We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts.
1 code implementation • 7 Mar 2022 • Johannes Schneider, Michail Vlachos
Our proposed `CLAssifier-DECoder' architecture (ClaDec) facilitates the understanding of the output of an arbitrary layer of neurons or subsets thereof.
no code implementations • 16 Feb 2022 • Johannes Schneider
The learning dynamics of deep neural networks are subject to controversy.
no code implementations • 4 Jan 2022 • Benjamin Balzer, Johannes Schneider
We introduce \emph{informational punishment} to the design of mechanisms that compete with an exogenous status quo mechanism: Players can send garbled public messages with some delay, and others cannot commit to ignoring them.
no code implementations • 2 Jan 2022 • Johannes Schneider, Robin Richner, Micha Riser
We also show how teachers can effectively control the type of errors made by the system and how they can validate efficiently that the autograder's performance on individual exams is close to the expected performance.
no code implementations • 14 Nov 2021 • Christoph Carnehl, Johannes Schneider
We show that the agent may return to the initial idea after having left it in the past to explore alternatives.
no code implementations • 7 Nov 2021 • Aditya Kuvalekar, João Ramos, Johannes Schneider
Agents, some with a bias, decide between undertaking a risky project and a safe alternative based on information about the project's efficiency.
1 code implementation • 10 Jun 2021 • Johannes Schneider
The data distribution commonly evolves over time leading to problems such as concept drift that often decrease classifier performance.
no code implementations • 26 Feb 2021 • Christoph Carnehl, Johannes Schneider
Researchers select a question and how intensely to study it.
no code implementations • 3 Dec 2020 • Marcus Basalla, Johannes Schneider, Jan vom Brocke
While the potential of deep learning (DL) for automating simple tasks is already well explored, recent research has started investigating the use of deep learning for creative design, both for complete artifact creation and supporting humans in the creation process.
1 code implementation • 27 Nov 2020 • Johannes Schneider, Michalis Vlachos
Humans possess a remarkable capability to make fast, intuitive decisions, but also to self-reflect, i. e., to explain to oneself, and to efficiently learn from explanations by others.
no code implementations • 20 Nov 2020 • Johannes Schneider, Rene Abraham, Christian Meske, Jan vom Brocke
Artificial Intelligence (AI) governance regulates the exercise of authority and control over the management of AI.
no code implementations • 19 Sep 2020 • Johannes Schneider
Humans rely more and more on systems with AI components.
no code implementations • 27 May 2020 • Johannes Schneider, Frank Breitinger
Artificial intelligence (AI) makes decisions impacting our daily lives in an increasingly autonomous manner.
1 code implementation • 27 May 2020 • Johannes Schneider, Michalis Vlachos
We present a `CLAssifier-DECoder' architecture (\emph{ClaDec}) which facilitates the comprehension of the output of an arbitrary layer in a neural network (NN).
no code implementations • 9 Mar 2020 • Johannes Schneider
Our theoretical analysis quantifies the learning behavior of weights of a single spatial filter.
no code implementations • 21 Jan 2020 • Johannes Schneider, Christian Meske, Michalis Vlachos
To address this issue, our work investigates how AI models (i. e., deep learning, and existing instruments to increase transparency regarding AI decisions) can be used to create and detect deceptive explanations.
no code implementations • 8 Dec 2019 • Johannes Schneider
We investigate how inputs of humans can be altered to reduce misinterpretation by the AI system and to improve efficiency of input generation for the human while altered inputs should remain as similar as possible to the original inputs.
no code implementations • 6 Sep 2019 • Johannes Schneider, Michail Vlachos
We discuss training techniques, objectives and metrics toward personalization of deep learning models.
no code implementations • 25 May 2019 • Johannes Schneider
This work investigates fundamental questions related to learning features in convolutional neural networks (CNN).
2 code implementations • 7 Oct 2017 • Johannes Schneider
Current topic models often suffer from discovering topics not matching human intuition, unnatural switching of topics within documents and high computational demands.
no code implementations • 10 Dec 2016 • Johannes Schneider, Thomas Locher
We evaluated our method using more than ten programmers as well as pattern mining across open source code repositories to gain insights of (micro-)coding patterns that are relevant for generating misleading statements.
Cryptography and Security