Algorithms to estimate Shapley value feature attributions
Feature attributions based on the Shapley value are popular for explaining machine
learning models. However, their estimation is complex from both theoretical and …
learning models. However, their estimation is complex from both theoretical and …
[HTML][HTML] Notions of explainability and evaluation approaches for explainable artificial intelligence
Abstract Explainable Artificial Intelligence (XAI) has experienced a significant growth over
the last few years. This is due to the widespread application of machine learning, particularly …
the last few years. This is due to the widespread application of machine learning, particularly …
[HTML][HTML] Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence
Artificial intelligence (AI) is currently being utilized in a wide range of sophisticated
applications, but the outcomes of many AI models are challenging to comprehend and trust …
applications, but the outcomes of many AI models are challenging to comprehend and trust …
Combining machine learning and computational chemistry for predictive insights into chemical systems
Machine learning models are poised to make a transformative impact on chemical sciences
by dramatically accelerating computational algorithms and amplifying insights available from …
by dramatically accelerating computational algorithms and amplifying insights available from …
A survey on neural network interpretability
Along with the great success of deep neural networks, there is also growing concern about
their black-box nature. The interpretability issue affects people's trust on deep learning …
their black-box nature. The interpretability issue affects people's trust on deep learning …
A survey on the explainability of supervised machine learning
N Burkart, MF Huber - Journal of Artificial Intelligence Research, 2021 - jair.org
Predictions obtained by, eg, artificial neural networks have a high accuracy but humans
often perceive the models as black boxes. Insights about the decision making are mostly …
often perceive the models as black boxes. Insights about the decision making are mostly …
Protein design with guided discrete diffusion
A popular approach to protein design is to combine a generative model with a discriminative
model for conditional sampling. The generative model samples plausible sequences while …
model for conditional sampling. The generative model samples plausible sequences while …
Knowledge neurons in pretrained transformers
Large-scale pretrained language models are surprisingly good at recalling factual
knowledge presented in the training corpus. In this paper, we present preliminary studies on …
knowledge presented in the training corpus. In this paper, we present preliminary studies on …
A unifying review of deep and shallow anomaly detection
Deep learning approaches to anomaly detection (AD) have recently improved the state of
the art in detection performance on complex data sets, such as large collections of images or …
the art in detection performance on complex data sets, such as large collections of images or …
Post-hoc interpretability for neural nlp: A survey
Neural networks for NLP are becoming increasingly complex and widespread, and there is a
growing concern if these models are responsible to use. Explaining models helps to address …
growing concern if these models are responsible to use. Explaining models helps to address …