相关论文: From Statistical Relational to Neurosymbolic Artif…
The development of large-scale artificial intelligence (AI) models is influencing neuroscience research by enabling end-to-end learning from raw brain signals and neural data. In this paper, we review applications of large-scale AI models…
Neuroscience and artificial intelligence are closely intertwined, but so are the physics of dynamical system, philosophy and psychology. Each of these fields try in their own way to relate observations at the level of molecules, synapses,…
Spatial reasoning is an important component of human intelligence. We can imagine the shapes of 3D objects and reason about their spatial relations by merely looking at their three-view line drawings in 2D, with different levels of…
A popular approach to neurosymbolic AI involves mapping logic formulas to arithmetic circuits (computation graphs consisting of sums and products) and passing the outputs of a neural network through these circuits. This approach enforces…
Classroom AI is rapidly expanding from low-level perception toward higher-level judgments about engagement, confusion, collaboration, and instructional quality. Yet classrooms are among the hardest real-world settings for multimodal vision:…
Alzheimer's disease (AD) diagnosis is complex, requiring the integration of imaging and clinical data for accurate assessment. While deep learning has shown promise in brain MRI analysis, it often functions as a black box, limiting…
The symbolic AI community is increasingly trying to embrace machine learning in neuro-symbolic architectures, yet is still struggling due to cultural barriers. To break the barrier, this rather opinionated personal memo attempts to explain…
Advancements in Artificial Intelligence (AI) and deep neural networks have driven significant progress in vision and text processing. However, achieving human-like reasoning and interpretability in AI systems remains a substantial…
It is generally accepted that all cyber attacks cannot be prevented, creating a need for the ability to detect and respond to cyber attacks. Both connectionist and symbolic AI are currently being used to support such detection and response.…
The computational demands of modern AI services are increasingly shifting execution beyond centralized clouds toward a computing continuum spanning edge and end devices. However, the scale, heterogeneity, and cross-layer dependencies of…
Neurosymbolic learning enables the integration of symbolic reasoning with deep learning but faces significant challenges in scaling to complex symbolic programs, large datasets, or both. We introduce DOLPHIN, a framework that tackles these…
In recent years, data-intensive AI, particularly the domain of natural language processing and understanding, has seen significant progress driven by the advent of large datasets and deep neural networks that have sidelined more classic AI…
Dialog Structure Induction (DSI) is the task of inferring the latent dialog structure (i.e., a set of dialog states and their temporal transitions) of a given goal-oriented dialog. It is a critical component for modern dialog system design…
The Theory of Proportions and Symbolic Allusions applied Interdisciplinary (TPASAI) is a framework that integrates mathematics, linguistics, psychology, and game theory to uncover hidden patterns and proportions in reality. Its central idea…
Semantic communication (SC) aims to communicate reliably with minimal data transfer while simultaneously providing seamless connectivity to heterogeneous services and users. In this paper, a novel emergent SC (ESC) system framework is…
In this paper we argue that Neuro-Symbolic AI (NeSy-AI) should be applied for patient monitoring. In this context, we introduce patient monitoring as a special case of Human Activity Recognition and derive concrete requirements for this…
Knowledge about space and time is necessary to solve problems in the physical world: An AI agent situated in the physical world and interacting with objects often needs to reason about positions of and relations between objects; and as soon…
Despite their linguistic competence, Large Language Models (LLMs) often struggle to reason reliably and flexibly. To identify these shortcomings, we introduce the Non-Linear Reasoning (NLR) dataset, a collection of 55 unique, hand-designed…
A cognitive architecture aimed at cumulative learning must provide the necessary information and control structures to allow agents to learn incrementally and autonomously from their experience. This involves managing an agent's goals as…
Binary semirings such as the tropical, log, and probability semirings form a core algebraic tool in classical and modern neural inference systems, supporting tasks like Viterbi decoding, dynamic programming, and probabilistic reasoning.…