Search Results for author:
Found 13 papers, 11 papers with code
Pix2Code: Learning to Compose Neural Visual Concepts as Programs
The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning.
Where is the Truth? The Risk of Getting Confounded in a Continual World
A dataset is confounded if it is most easily solved via a spurious correlation which fails to generalize to new data.
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
Unfortunately, the black-box nature of deep neural networks impedes the inclusion of domain experts for inspecting the model and revising suboptimal policies.
Learning by Self-Explaining
Current AI research mainly treats explanations as a means for model inspection.
Learning to Intervene on Concept Bottlenecks
Specifically, a CB2M learns to generalize interventions to appropriate novel situations via a two-fold memory with which it can learn to detect mistakes and to reapply previous interventions.
V-LoL: A Diagnostic Dataset for Visual Logical Learning
Despite the successes of recent developments in visual AI, different shortcomings still exist; from missing exact logical reasoning, to abstract generalization abilities, to understanding complex and noisy scenes.
Boosting Object Representation Learning via Motion and Object Continuity
Recent unsupervised multi-object detection models have shown impressive performance improvements, largely attributed to novel architectural inductive biases.
Revision Transformers: Instructing Language Models to Change their Values
In this work, we question the current common practice of storing all information in the model parameters and propose the Revision Transformer (RiT) to facilitate easy model updating.
A Typology for Exploring the Mitigation of Shortcut Behavior
In addition, we discuss existing and introduce novel measures and benchmarks for evaluating the overall abilities of a XIL method.
Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations
In this work, we show the advantages of prototype representations for understanding and revising the latent space of neural concept learners.
SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming
The probability estimates resulting from NPPs act as the binding element between the logical program and raw input data, thereby allowing SLASH to answer task-dependent logical queries.
Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations
Most explanation methods in deep learning map importance estimates for a model's prediction back to the original input space.
Making deep neural networks right for the right scientific reasons by interacting with their explanations
Deep neural networks have shown excellent performances in many real-world applications.
