Search Results for author:
Found 34 papers, 8 papers with code
Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda
To this end, we focus on surveying existing works.
Governance of Generative Artificial Intelligence for Companies
Generative Artificial Intelligence (GenAI), specifically large language models like ChatGPT, has swiftly entered organizations without adequate governance, posing both opportunities and risks.
Understanding and Leveraging the Learning Phases of Neural Networks
The learning dynamics of deep neural networks are not well understood.
Negotiating with LLMS: Prompt Hacks, Skill Gaps, and Reasoning Deficits
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.
Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions
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)
Improving classifier decision boundaries using nearest neighbors
Neural networks are not learning optimal decision boundaries.
Towards LLM-based Autograding for Short Textual Answers
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.
Implementing Smart Contracts: The case of NFT-rental with pay-per-like
Non-fungible tokens(NFTs) are on the rise.
SoK: Pragmatic Assessment of Machine Learning for Network Intrusion Detection
Unfortunately, the value of ML for NID depends on a plethora of factors, such as hardware, that are often neglected in scientific literature.
Efficient and Flexible Topic Modeling using Pretrained Embeddings and Bag of Sentences
Pre-trained language models have led to a new state-of-the-art in many NLP tasks.
A Survey of Deep Learning: From Activations to Transformers
Deep learning has made tremendous progress in the last decade.
Foundation models in brief: A historical, socio-technical focus
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.
Concept-based Adversarial Attacks: Tricking Humans and Classifiers Alike
We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts.
Explaining Classifiers by Constructing Familiar Concepts
Our proposed `CLAssifier-DECoder' architecture (ClaDec) facilitates the understanding of the output of an arbitrary layer of neurons or subsets thereof.
The learning phases in NN: From Fitting the Majority to Fitting a Few
The learning dynamics of deep neural networks are subject to controversy.
Mechanism Design with Informational Punishment
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.
Towards Trustworthy AutoGrading of Short, Multi-lingual, Multi-type Answers
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.
On Risk and Time Pressure: When to Think and When to Do
We show that the agent may return to the initial idea after having left it in the past to explore alternatives.
The Wrong Kind of Information
Agents, some with a bias, decide between undertaking a risky project and a safe alternative based on information about the project's efficiency.
Domain Transformer: Predicting Samples of Unseen, Future Domains
The data distribution commonly evolves over time leading to problems such as concept drift that often decrease classifier performance.
Creativity of Deep Learning: Conceptualization and Assessment
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.
Reflective-Net: Learning from Explanations
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.
AI Governance for Businesses
Artificial Intelligence (AI) governance regulates the exercise of authority and control over the management of AI.
Humans learn too: Better Human-AI Interaction using Optimized Human Inputs
Humans rely more and more on systems with AI components.
Towards AI Forensics: Did the Artificial Intelligence System Do It?
Artificial intelligence (AI) makes decisions impacting our daily lives in an increasingly autonomous manner.
Explaining Neural Networks by Decoding Layer Activations
We present a `CLAssifier-DECoder' architecture (\emph{ClaDec}) which facilitates the comprehension of the output of an arbitrary layer in a neural network (NN).
Correlated Initialization for Correlated Data
Our theoretical analysis quantifies the learning behavior of weights of a single spatial filter.
Deceptive AI Explanations: Creation and Detection
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.
Human-to-AI Coach: Improving Human Inputs to AI Systems
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.
Personalization of Deep Learning
We discuss training techniques, objectives and metrics toward personalization of deep learning models.
Locality-Promoting Representation Learning
This work investigates fundamental questions related to learning features in convolutional neural networks (CNN).
Topic Modeling based on Keywords and Context
Current topic models often suffer from discovering topics not matching human intuition, unnatural switching of topics within documents and high computational demands.
Obfuscation using Encryption
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
