Related papers: A neural network for modeling human concept format…

This paper proposes a user semantic intent modeling algorithm based on Capsule Networks to address the problem of insufficient accuracy in intent recognition for human-computer interaction. The method represents semantic features in input…

The question how neural systems (of humans) can perform reasoning is still far from being solved. We posit that the process of forming Concepts is a fundamental step required for this. We argue that, first, Concepts are formed as closed…

Although neural models have achieved remarkable performance, they still encounter doubts due to the intransparency. To this end, model prediction explanation is attracting more and more attentions. However, current methods rarely…

Neural networks deliver impressive predictive performance across a variety of tasks, but they are often opaque in their decision-making processes. Despite a growing interest in mechanistic interpretability, tools for systematically…

As applications of generative AI become mainstream, it is important to understand what generative models are capable of producing, and the extent to which one can predictably control their outputs. In this paper, we propose a visualization…

When people try to understand nuanced language they typically process multiple input sensor modalities to complete this cognitive task. It turns out the human brain has even a specialized neuron formation, called sagittal stratum, to help…

Humans continually expand their learned knowledge to new domains and learn new concepts without any interference with past learned experiences. In contrast, machine learning models perform poorly in a continual learning setting, where input…

This article presents a concept-centric paradigm for building agents that can learn continually and reason flexibly. The concept-centric agent utilizes a vocabulary of neuro-symbolic concepts. These concepts, such as object, relation, and…

Semantic memory is the subsystem of human memory that stores knowledge of concepts or meanings, as opposed to life specific experiences. The organization of concepts within semantic memory can be understood as a semantic network, where the…

We consider the implications of the mathematical analysis of neurone-to-neurone dynamical complex networks. We show how the dynamical behaviour of small scale strongly connected networks lead naturally to non-binary information processing…

Humans possess the capability to reason at an abstract level and to structure information into abstract categories, but the underlying neural processes have remained unknown. Experimental evidence has recently emerged for the organization…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Neural networks are powerful tools for cognitive modeling due to their flexibility and emergent properties. However, interpreting their learned representations remains challenging due to their sub-symbolic semantics. In this work, we…

Humans can infer concepts from image pairs and apply those in the physical world in a completely different setting, enabling tasks like IKEA assembly from diagrams. If robots could represent and infer high-level concepts, it would…

How perception and reasoning arise from neuronal network activity is poorly understood. This is reflected in the fundamental limitations of connectionist artificial intelligence, typified by deep neural networks trained via gradient-based…

The human brain is a dynamical system whose extremely complex sensor-driven neural processes give rise to conceptual, logical cognition. Understanding the interplay between nonlinear neural dynamics and concept-level cognition remains a…

Humans possess a remarkable ability to acquire knowledge efficiently and apply it across diverse modalities through a coherent and shared understanding of the world. Inspired by this cognitive capability, we introduce a concept-centric…

Concept-based interpretability for Convolutional Neural Networks (CNNs) aims to align internal model representations with high-level semantic concepts, but existing approaches largely overlook the semantic roles of individual filters and…

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Inspired by the recent neuroscience studies on the left-right asymmetry of the human brain in processing low and high spatial frequency information, this paper introduces a dual skipping network which carries out coarse-to-fine object…