Approximate and Situated Causality in Deep Learning

Vallverdú, Jordi

doi:10.20944/preprints201907.0110.v1

Cited by 3 publications

(2 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Granted, while explainability clarifies AutoML processes/outputs and can highlight biases, how these explanations are interpreted still depend heavily on human cognitive behaviour. For continued progress in this area, it is crucial to examine how humans do causal inference [12] and how they grapple with issues of ambiguity and uncertainty in learning algorithms [300]. Indeed, examining the heuristic operations of a human brain can lead to the improved design/development of ML models that are both causal and explainable [264].…”

Section: Bias Mitigation Through Human-computer Collaborationmentioning

confidence: 99%

The Roles and Modes of Human Interactions with Automated Machine Learning Systems

Khuat¹,

Kedziora²,

Gabrys³

2022

Preprint

View full text Add to dashboard Cite

As automated machine learning (AutoML) systems continue to progress in both sophistication and performance, it becomes important to understand the 'how' and 'why' of human-computer interaction (HCI) within these frameworks, both current and expected. Such a discussion is necessary for optimal system design, leveraging advanced data-processing capabilities to support decision-making involving humans, but it is also key to identifying the opportunities and risks presented by ever-increasing levels of machine autonomy. Within this context, we focus on the following questions: (i) How does HCI currently look like for state-of-the-art AutoML algorithms, especially during the stages of development, deployment, and maintenance? (ii) Do the expectations of HCI within AutoML frameworks vary for different types of users and stakeholders? (iii) How can HCI be managed so that AutoML solutions acquire human trust and broad acceptance? (iv) As AutoML systems become more autonomous and capable of learning from complex open-ended environments, will the fundamental nature of HCI evolve? To consider these questions, we project existing literature in HCI into the space of AutoML; this connection has, to date, largely been unexplored. In so doing, we review topics including user-interface design, human-bias mitigation, and trust in artificial intelligence (AI). Additionally, to rigorously gauge the future of HCI, we contemplate how AutoML may manifest in effectively open-ended environments. This discussion necessarily reviews projected developmental pathways for AutoML, such as the incorporation of reasoning, although the focus remains on how and why HCI may occur in such a framework rather than on any implementational details. Ultimately, this review serves to identify key research directions aimed at better facilitating the roles and modes of human interactions with both current and future AutoML systems.

show abstract

Section: Bias Mitigation Through Human-computer Collaborationmentioning

confidence: 99%

The Roles and Modes of Human Interactions with Automated Machine Learning Systems

Khuat¹,

Kedziora²,

Gabrys³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Fig. 1 illustrates the process of explainable artificial intelligence (XAI) technique [10]. This paper presents an XAI based intrusion detection system (IDS) using feature selection with Dirichlet Variational Autoencoder (XAIIDS-FSDVAE) model for CPS.…”

Section: Introductionmentioning

confidence: 99%

Optimal Machine Learning Enabled Intrusion Detection in Cyber-Physical System Environment

Alqaralleh¹,

Aldhaban²,

AlQarallehs³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Cyber-attacks on cyber-physical systems (CPSs) resulted to sensing and actuation misbehavior, severe damage to physical object, and safety risk. Machine learning (ML) models have been presented to hinder cyberattacks on the CPS environment; however, the non-existence of labelled data from new attacks makes their detection quite interesting. Intrusion Detection System (IDS) is a commonly utilized to detect and classify the existence of intrusions in the CPS environment, which acts as an important part in secure CPS environment. Latest developments in deep learning (DL) and explainable artificial intelligence (XAI) stimulate new IDSs to manage cyberattacks with minimum complexity and high sophistication. In this aspect, this paper presents an XAI based IDS using feature selection with Dirichlet Variational Autoencoder (XAIIDS-FSDVAE) model for CPS. The proposed model encompasses the design of coyote optimization algorithm (COA) based feature selection (FS) model is derived to select an optimal subset of features. Next, an intelligent Dirichlet Variational Autoencoder (DVAE) technique is employed for the anomaly detection process in the CPS environment. Finally, the parameter optimization of the DVAE takes place using a manta ray foraging optimization (MRFO) model to tune the parameter of the DVAE. In order to determine the enhanced intrusion detection efficiency of the XAIIDS-FSDVAE technique, a wide range of simulations take place using the benchmark datasets. The experimental results reported the better performance of the XAIIDS-FSDVAE technique over the recent methods in terms of several evaluation parameters.

show abstract

Machine learning in the EU health care context: exploring the ethical, legal and social issues

Miguel

Sanz

Moratinos

2020

Information, Communication & Society

View full text Add to dashboard Cite

The diagnosis and clinical decision making based on Machine Learning technologies are showing significant advances that may change the functioning of our health care systems. These advances promise more effective and efficient healthcare, at a lower cost. This may allow healthcare professionals to recover 'high-touch' time with their patients. The evidence suggests that all these promises have yet to be demonstrated in clinical practice, but what is undeniable is that these technologies are resignifying the relationships in the health landscape, particularly the physician-patient relationship, which we could already redefine as "physiciancomputer-patient relationship". Although it is true that today fully automated decision systems are scarce in comparison with integrative decision support systems, we cannot fail to observe the horizon they define. Our most recent regulatory framework, defined by the General Regulation on Data Protection, has tried to avoid this scenario by including the right not to be subject to a decision based solely on automated processing. In this paper, however, we argue that this legal tool is adequate but not sufficient to address the legal, ethical and social challenges that Machine Learning technologies pose to patients' rights and health care givers' capacities.

show abstract

Approximate and Situated Causality in Deep Learning

Cited by 3 publications

References 50 publications

The Roles and Modes of Human Interactions with Automated Machine Learning Systems

The Roles and Modes of Human Interactions with Automated Machine Learning Systems

Optimal Machine Learning Enabled Intrusion Detection in Cyber-Physical System Environment

Machine learning in the EU health care context: exploring the ethical, legal and social issues

Contact Info

Product

Resources

About