Results 201 to 210 of about 43,008 (285)

Embedded Interactions and Selective Disclosure: Network Effects on Conversations aboard Skylab

Symbolic Interaction, EarlyView.
How do absent others influence our interactions? We argue in this paper that interactions are embedded within networks formed by chains of specific relationships between known third parties. The anticipation of future interactions with external others conditions our interpretation of the current situation and affects our behavior in the interaction. We
Michael Schultz, Leslie DeChurch, Noshir Contractor   +2 more
wiley   +1 more source

Designing effective explainable AI: a human-centered evaluation of explanation formats in financial decision-making. [PDF]

Front Artif Intell
Maathuis H, Stalenhoef M, van Otterloo S, Zwaal R, van Montfort K, Sent D.   +5 more
europepmc   +1 more source

Knowledge of Counterfactuals

Royal Institute of Philosophy Supplement, 2009
openaire   +2 more sources

From prediction to intervention: Paradigm shifts in causal AI for precision medicine and large‐scale cohorts

VIEW, EarlyView.
Large‐scale cohorts and multimodal biomedical data have enabled powerful predictive models for clinical risk stratification, but prediction alone cannot guide effective interventions. This review introduces causal artificial intelligence as a design‐first framework that integrates target trial emulation, causal discovery, and robust effect estimation ...
Linlin Cao, Yudian Xu, Yifan Chen, Honghao Huang, Wei Xu, Jun Pu   +5 more
wiley   +1 more source

Breast Cancer Prediction Using Rotation Forest Algorithm Along with Finding the Influential Causes. [PDF]

Bioengineering (Basel)
Das P, Sarker P, Tiang JJ, Nahid AA.
europepmc   +1 more source

Generating Compressed Counterfactual Hard Negative Samples for Graph Contrastive Learning

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Graph contrastive learning (GCL) relies on acquiring high‐quality positive and negative samples to learn the structural semantics of the input graph. Previous approaches typically sampled negative samples from the same training batch or an irrelevant external graph.
Haoran Yang, Hongxu Chen, Xiangyu Zhao, Sixiao Zhang, Xiangguo Sun, Qian Li, Hongzhi Yin, Guandong Xu   +7 more
wiley   +1 more source

The causal effect of parent occupation on child occupation: A multivalued treatment with positivity constraints. [PDF]

Sociol Methods Res
Lundberg I, Molitor D, Brand JE.
europepmc   +1 more source

Multitype Game Optimisation: A Two‐Stage Fine‐Tuning Framework for Multi‑Game Optimisation With Large Language Models

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Large language models (LLMs) have made remarkable advances in natural language processing, demonstrating great potential in modelling structured sequences. However, adapting these capabilities to machine gaming tasks such as Go remains challenging due to limitations in strategy generalisation and optimisation efficiency.
Xiali Li, Jingshi Gu, Feifan He, Yang Xiao, Yuanli Jia, Ping Lan   +5 more
wiley   +1 more source

Does neural computation feel like something? [PDF]

Front Neurosci
Gidon A, Aru J, Larkum ME.
europepmc   +1 more source

Neural Network Repair With Shapley‐Guided Search

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT The deployment of deep neural networks (DNNs) in safety‐critical domains is critically hampered by their vulnerability to defects, which can arise from malicious attacks or low‐quality data. Therefore, precisely locating the network components responsible for these defects, and subsequently repairing them without compromising overall model ...
Xiaofu Du, Zixiong Zhang, Xuesong Wang, Linqiang Liu, Junyan Qian   +4 more
wiley   +1 more source