A neuro-vector-symbolic architecture for solving Raven's progressive matrices
Neither deep neural networks nor symbolic artificial intelligence (AI) alone has approached
the kind of intelligence expressed in humans. This is mainly because neural networks are …
the kind of intelligence expressed in humans. This is mainly because neural networks are …
Investigating data contamination in modern benchmarks for large language models
Recent observations have underscored a disparity between the inflated benchmark scores
and the actual performance of LLMs, raising concerns about potential contamination of …
and the actual performance of LLMs, raising concerns about potential contamination of …
Integration of neuromorphic AI in event-driven distributed digitized systems: Concepts and research directions
Increasing complexity and data-generation rates in cyber-physical systems and the
industrial Internet of things are calling for a corresponding increase in AI capabilities at the …
industrial Internet of things are calling for a corresponding increase in AI capabilities at the …
Sample-efficient learning of novel visual concepts
Despite the advances made in visual object recognition, state-of-the-art deep learning
models struggle to effectively recognize novel objects in a few-shot setting where only a …
models struggle to effectively recognize novel objects in a few-shot setting where only a …
Knowledge-guided short-context action anticipation in human-centric videos
This work focuses on anticipating long-term human actions, particularly using short video
segments, which can speed up editing workflows through improved suggestions while …
segments, which can speed up editing workflows through improved suggestions while …
Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures
Abstract reasoning is a cornerstone of human intelligence, and replicating it with artificial
intelligence (AI) presents an ongoing challenge. This study focuses on efficiently solving …
intelligence (AI) presents an ongoing challenge. This study focuses on efficiently solving …
Interactive Visual Task Learning for Robots
We present a framework for robots to learn novel visual concepts and visual tasks via in-situ
linguistic interactions with human users. Previous approaches in computer vision have …
linguistic interactions with human users. Previous approaches in computer vision have …
[图书][B] Neuro Symbolic Reasoning and Learning
In this chapter, we introduce propositional logic and first order predicate calculus, adapted to
the way we make use of these languages in the rest of this book 1—given that we wish to …
the way we make use of these languages in the rest of this book 1—given that we wish to …
Synapse: Learning Preferential Concepts from Visual Demonstrations
This paper addresses the problem of preference learning, which aims to learn user-specific
preferences (eg," good parking spot"," convenient drop-off location") from visual input …
preferences (eg," good parking spot"," convenient drop-off location") from visual input …
Towards Learning Abductive Reasoning using VSA Distributed Representations
G Camposampiero, M Hersche, A Terzić… - arXiv preprint arXiv …, 2024 - arxiv.org
We introduce the Abductive Rule Learner with Context-awareness (ARLC), a model that
solves abstract reasoning tasks based on Learn-VRF. ARLC features a novel and more …
solves abstract reasoning tasks based on Learn-VRF. ARLC features a novel and more …