Zobrazeno 1 - 10
of 268
pro vyhledávání: '"Garcez, Artur"'
Ensuring the reliability and safety of automated decision-making is crucial. It is well-known that data distribution shifts in machine learning can produce unreliable outcomes. This paper proposes a new approach for measuring the reliability of predi
Externí odkaz:
http://arxiv.org/abs/2407.07821
Autor:
Sikar, Daniel, Garcez, Artur, Bloomfield, Robin, Weyde, Tillman, Peeroo, Kaleem, Singh, Naman, Hutchinson, Maeve, Laksono, Dany, Reljan-Delaney, Mirela
This study introduces the Misclassification Likelihood Matrix (MLM) as a novel tool for quantifying the reliability of neural network predictions under distribution shifts. The MLM is obtained by leveraging softmax outputs and clustering techniques t
Externí odkaz:
http://arxiv.org/abs/2407.07818
Autor:
Sikar, Daniel, Garcez, Artur
We posit that data can only be safe to use up to a certain threshold of the data distribution shift, after which control must be relinquished by the autonomous system and operation halted or handed to a human operator. With the use of a computer visi
Externí odkaz:
http://arxiv.org/abs/2406.20046
Multivariate time series have many applications, from healthcare and meteorology to life science. Although deep learning models have shown excellent predictive performance for time series, they have been criticised for being "black-boxes" or non-inte
Externí odkaz:
http://arxiv.org/abs/2311.16834
Autor:
White, Adam, Saranti, Margarita, Garcez, Artur d'Avila, Hope, Thomas M. H., Price, Cathy J., Bowman, Howard
Machine learning offers great potential for automated prediction of post-stroke symptoms and their response to rehabilitation. Major challenges for this endeavour include the very high dimensionality of neuroimaging data, the relatively small size of
Externí odkaz:
http://arxiv.org/abs/2310.19174
Autor:
Pontelli, Enrico, Costantini, Stefania, Dodaro, Carmine, Gaggl, Sarah, Calegari, Roberta, Garcez, Artur D'Avila, Fabiano, Francesco, Mileo, Alessandra, Russo, Alessandra, Toni, Francesca
Publikováno v:
EPTCS 385, 2023
This volume contains the Technical Communications presented at the 39th International Conference on Logic Programming (ICLP 2023), held at Imperial College London, UK from July 9 to July 15, 2023. Technical Communications included here concern the Ma
Externí odkaz:
http://arxiv.org/abs/2308.14898
Despite the extensive investment and impressive recent progress at reasoning by similarity, deep learning continues to struggle with more complex forms of reasoning such as non-monotonic and commonsense reasoning. Non-monotonicity is a property of no
Externí odkaz:
http://arxiv.org/abs/2305.02171
Autor:
Odense, Simon, Garcez, Artur d'Avila
The field of neuro-symbolic AI aims to benefit from the combination of neural networks and symbolic systems. A cornerstone of the field is the translation or encoding of symbolic knowledge into neural networks. Although many neuro-symbolic methods an
Externí odkaz:
http://arxiv.org/abs/2212.12050
Encoder-decoder architectures are prominent building blocks of state-of-the-art solutions for tasks across multiple fields where deep learning (DL) or foundation models play a key role. Although there is a growing community working on the provision o
Externí odkaz:
http://arxiv.org/abs/2210.07117
Publikováno v:
1st Workshop on Human and Machine Decisions (WHMD 2021), NeurIPS 2021
We propose neural-symbolic integration for abstract concept explanation and interactive learning. Neural-symbolic integration and explanation allow users and domain-experts to learn about the data-driven decision making process of large neural models
Externí odkaz:
http://arxiv.org/abs/2112.11805