12 citations · 41 across the 13 of their papers we have counts for
19 papers
Efficient and Flexible Topic Modeling using Pretrained Embeddings and Bag of Sentences
Johannes Schneider
Pre-trained language models have led to a new state-of-the-art in many NLP tasks. However, for topic modeling, statistical generative models such as LDA are still prevalent, which…
A Survey of Deep Learning: From Activations to Transformers
Johannes Schneider, Michalis Vlachos
Deep learning has made tremendous progress in the last decade. A key success factor is the large amount of architectures, layers, objectives, and optimization techniques. They incl…
Foundation models in brief: A historical, socio-technical focus
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. These models achieve state-of…
Concept-based Adversarial Attacks: Tricking Humans and Classifiers Alike
Johannes Schneider, Giovanni Apruzzese
We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts. The original sample is shifted towards a target sampl…
Explaining Classifiers by Constructing Familiar Concepts
Johannes Schneider, Michail Vlachos
Interpreting a large number of neurons in deep learning is difficult. Our proposed `CLAssifier-DECoder' architecture (ClaDec) facilitates the understanding of the output of an arbi…
The learning phases in NN: From Fitting the Majority to Fitting a Few
Johannes Schneider
The learning dynamics of deep neural networks are subject to controversy. Using the information bottleneck (IB) theory separate fitting and compression phases have been put forward…
Towards Trustworthy AutoGrading of Short, Multi-lingual, Multi-type Answers
Johannes Schneider, Robin Richner, Micha Riser
Autograding short textual answers has become much more feasible due to the rise of NLP and the increased availability of question-answer pairs brought about by a shift to online ed…
Domain Transformer: Predicting Samples of Unseen, Future Domains
Johannes Schneider
The data distribution commonly evolves over time leading to problems such as concept drift that often decrease classifier performance. Current techniques are not adequate for this…
Creativity of Deep Learning: Conceptualization and Assessment
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 desi…
Reflective-Net: Learning from Explanations
Johannes Schneider, Michalis Vlachos
We examine whether data generated by explanation techniques, which promote a process of self-reflection, can improve classifier performance. Our work is based on the idea that huma…
Humans learn too: Better Human-AI Interaction using Optimized Human Inputs
Johannes Schneider
Humans rely more and more on systems with AI components. The AI community typically treats human inputs as a given and optimizes AI models only. This thinking is one-sided and it n…
Towards AI Forensics: Did the Artificial Intelligence System Do It?
Johannes Schneider, Frank Breitinger
Artificial intelligence (AI) makes decisions impacting our daily lives in an increasingly autonomous manner. Their actions might cause accidents, harm, or, more generally, violate…
Explaining Neural Networks by Decoding Layer Activations
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). It uses a decoder t…
Correlated Initialization for Correlated Data
Johannes Schneider
Spatial data exhibits the property that nearby points are correlated. This also holds for learnt representations across layers, but not for commonly used weight initialization meth…
Deceptive AI Explanations: Creation and Detection
Johannes Schneider, Christian Meske, Michalis Vlachos
Artificial intelligence (AI) comes with great opportunities but can also pose significant risks. Automatically generated explanations for decisions can increase transparency and fo…
Human-to-AI Coach: Improving Human Inputs to AI Systems
Johannes Schneider
Humans increasingly interact with Artificial intelligence(AI) systems. AI systems are optimized for objectives such as minimum computation or minimum error rate in recognizing and…
Personalization of Deep Learning
Johannes Schneider, Michail Vlachos
We discuss training techniques, objectives and metrics toward personalization of deep learning models. In machine learning, personalization addresses the goal of a trained model to…
Locality-Promoting Representation Learning
Johannes Schneider
This work investigates fundamental questions related to learning features in convolutional neural networks (CNN). Empirical findings across multiple architectures such as VGG, ResN…
Personalized explanation in machine learning: A conceptualization
Johanes Schneider, Joshua Handali
Explanation in machine learning and related fields such as artificial intelligence aims at making machine learning models and their decisions understandable to humans. Existing wor…