There Is Hope After All: Quantifying Opinion and Trustworthiness in Neural Networks.
Mingxi Cheng,Shahin Nazarian,Paul Bogdan +2 more
- Vol. 3, pp 54-54
Reads0
Chats0
TLDR
DeepTrust identifies proper multi-layered neural network (NN) topologies that have high projected trust probabilities, even when trained with untrusted data, and shows that uncertain opinion of data is not always malicious while evaluating NN's opinion and trustworthiness, whereas the disbelief opinion hurts trust the most.Abstract:
Artificial Intelligence (AI) plays a fundamental role in the modern world, especially when used as an autonomous decision maker. One common concern nowadays is "how trustworthy the AIs are." Human operators follow a strict educational curriculum and performance assessment that could be exploited to quantify how much we entrust them. To quantify the trust of AI decision makers, we must go beyond task accuracy especially when facing limited, incomplete, misleading, controversial or noisy datasets. Toward addressing these challenges, we describe DeepTrust, a Subjective Logic (SL) inspired framework that constructs a probabilistic logic description of an AI algorithm and takes into account the trustworthiness of both dataset and inner algorithmic workings. DeepTrust identifies proper multi-layered neural network (NN) topologies that have high projected trust probabilities, even when trained with untrusted data. We show that uncertain opinion of data is not always malicious while evaluating NN's opinion and trustworthiness, whereas the disbelief opinion hurts trust the most. Also trust probability does not necessarily correlate with accuracy. DeepTrust also provides a projected trust probability of NN's prediction, which is useful when the NN generates an over-confident output under problematic datasets. These findings open new analytical avenues for designing and improving the NN topology by optimizing opinion and trustworthiness, along with accuracy, in a multi-objective optimization formulation, subject to space and time constraints.read more
Citations
More filters
Journal ArticleDOI
A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer's disease.
Shaker El-Sappagh,Shaker El-Sappagh,Jose M. Alonso,S. M. Riazul Islam,Ahmad M. Sultan,Kyung Sup Kwak +5 more
TL;DR: In this paper, a two-layer model with random forest (RF) as classifier algorithm is proposed to diagnose and progression detection of Alzheimer's disease (AD) in patients.
Journal ArticleDOI
Machine Learning and Deep Learning Approaches for Brain Disease Diagnosis: Principles and Recent Advances
Protima Khan,Md. Fazlul Kader,S. M. Riazul Islam,Aisha B. Rahman,Md. Shahriar Kamal,Masbah Uddin Toha,Kyung Sup Kwak +6 more
TL;DR: This study aims at finding the most accurate technique for detecting different brain diseases which can be employed for future betterment through a review on recent machine learning and deep learning approaches in detecting four brain diseases such as Alzheimer's disease, brain tumor, epilepsy, and Parkinson's disease.
Journal ArticleDOI
Smartphone-based DNA diagnostics for malaria detection using deep learning for local decision support and blockchain technology for security
Xin Guo,Muhammad Khalid,Ivo Domingos,Anna Lito Michala,Moses Adriko,Candia Rowel,Diana Ajambo,Alice Garrett,Shantimoy Kar,Xiaoxiang Yan,Julien Reboud,Edridah M. Tukahebwa,Jonathan M. Cooper +12 more
TL;DR: A smartphone-based end-to-end platform for multiplexed DNA diagnosis of malaria that uses a low-cost paper-based microfluidic diagnostic test, combined with deep learning algorithms for local decision support and blockchain technology for secure data connectivity and management is reported.
Journal ArticleDOI
Interpretability and fairness evaluation of deep learning models on MIMIC-IV dataset
TL;DR: In this paper , the authors focus on MIMIC-IV (Medical Information Mart for Intensive Care, version IV), the largest publicly available healthcare dataset, and conduct comprehensive analyses of interpretability as well as dataset representation bias and prediction fairness of deep learning models for in-hospital mortality prediction.
Posted ContentDOI
Reduced false positives in autism screening via digital biomarkers inferred from deep comorbidity patterns
Dmytro Onishchenko,Yi Huang,James van Horne,Peter K. Smith,Peter K. Smith,Michael E. Msall,Ishanu Chattopadhyay +6 more
TL;DR: The Autism Co-morbid Risk Score (ACoR), which predicts elevated risk during the earliest childhood years, when interventions are the most effective, is adopted in practice and could significantly reduce the median diagnostic age for ASD, and reduce long post-screen wait-times experienced by families for confirmatory diagnoses and access to evidence based interventions.
References
More filters
Proceedings Article
Rectified Linear Units Improve Restricted Boltzmann Machines
Vinod Nair,Geoffrey E. Hinton +1 more
TL;DR: Restricted Boltzmann machines were developed using binary stochastic hidden units that learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset.
Proceedings Article
Deep Sparse Rectifier Neural Networks
TL;DR: This paper shows that rectifying neurons are an even better model of biological neurons and yield equal or better performance than hyperbolic tangent networks in spite of the hard non-linearity and non-dierentiabil ity.
Book ChapterDOI
Upper and Lower Probabilities Induced by a Multivalued Mapping
TL;DR: A distinctive feature of the present approach is a rule for conditioning, or more generally, arule for combining sources of information, as discussed in Sects.
Upper and Lower Probabilities Induced by a Multivalued Mapping.
TL;DR: In this paper, a multivalued mapping from a space X to a space S carries a probability measure defined over subsets of X into a system of upper and lower probabilities over S. Some basic properties of such systems are explored in Sects. 1 and 2.
Journal ArticleDOI
A logic for default reasoning
TL;DR: This paper proposes a logic for default reasoning, develops a complete proof theory and shows how to interface it with a top down resolution theorem prover, and provides criteria under which the revision of derived beliefs must be effected.