Author name cluster

Manuel de Sousa Ribeiro

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

NeSy Conference 2025 Conference Paper

Concept Probing: Where to Find Human-Defined Concepts

Manuel de Sousa Ribeiro
Afonso Leote
João Leite 0001

Concept probing has recently gained popularity as a way for humans to peek into what is encoded within artificial neural networks. In concept probing, additional classifiers are trained to map the internal representations of a model into human-defined concepts of interest. However, the performance of these probes is highly dependent on the internal representations they probe from, making identifying the appropriate layer to probe an essential task. In this paper, we propose a method to automatically identify which layer’s representations in a neural network model should be considered when probing for a given human-defined concept of interest, based on how informative and regular the representations are with respect to the concept. We validate our findings through an exhaustive empirical analysis over different neural network models and datasets.

Details

ECAI Conference 2025 Conference Paper

On the Performance of Concept Probing: The Influence of the Data

Manuel de Sousa Ribeiro
Afonso Leote
João Leite 0001

Concept probing has recently garnered increasing interest as a way to help interpret artificial neural networks, dealing both with their typically large size and their subsymbolic nature, which ultimately renders them unfeasible for direct human interpretation. Concept probing works by training additional classifiers to map the internal representations of a model into human-defined concepts of interest, thus allowing humans to peek inside artificial neural networks. Research on concept probing has mainly focused on the model being probed or the probing model itself, paying limited attention to the data required to train such probing models. In this paper, we address this gap. Focusing on concept probing in the context of image classification tasks, we investigate the effect of the data used to train probing models on their performance. We also make available concept labels for two widely used datasets.

Details

KR Conference 2022 Conference Paper

Looking Inside the Black-Box: Logic-based Explanations for Neural Networks

João Ferreira
Manuel de Sousa Ribeiro
Ricardo Gonçalves
João Leite

Deep neural network-based methods have recently enjoyed great popularity due to their effectiveness in solving difficult tasks. Requiring minimal human effort, they have turned into an almost ubiquitous solution in multiple domains. However, due to the size and complexity of typical neural network models' architectures, as well as the sub-symbolical nature of the representations generated by their neuronal activations, neural networks are essentially opaque, making it nearly impossible to explain to humans the reasoning behind their decisions. We address this issue by developing a procedure to induce human-understandable logic-based theories that attempt to represent the classification process of a given neural network model, based on the idea of establishing mappings from the values of the activations produced by the neurons of that model to human-defined concepts to be used in the induced logic-based theory. Exploring the setting of a synthetic image classification task, we provide empirical results to assess the quality of the developed theories for different neural network models, compare them to existing theories on that task, and give evidence that the theories developed through our method are faithful to the representations learned by the neural networks that they are built to describe.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Aligning Artificial Neural Networks and Ontologies towards Explainable AI

Manuel de Sousa Ribeiro
João Leite

Neural networks have been the key to solve a variety of different problems. However, neural network models are still regarded as black boxes, since they do not provide any humaninterpretable evidence as to why they output a certain result. We address this issue by leveraging on ontologies and building small classifiers that map a neural network model’s internal state to concepts from an ontology, enabling the generation of symbolic justifications for the output of neural network models. Using an image classification problem as testing ground, we discuss how to map the internal state of a neural network to the concepts of an ontology, examine whether the results obtained by the established mappings match our understanding of the mapped concepts, and analyze the justifications obtained through this method.

PDF Details