4.5 Article

Learning dynamic causal mechanisms from non-stationary data

Related references

Note: Only part of the references are listed.
Article Computer Science, Artificial Intelligence

CMGAN: A generative adversarial network embedded with causal matrix

Wenbin Zhang et al.

Summary: This study explores the relationship between different features in multi-label learning and generates controllable features of multi-label images. A generative adversarial network with a nested structural causal mechanism is designed to achieve this goal, allowing for causal relationship learning and feature separation on a causal level. An intervention mechanism is added during the label generation process and the effectiveness is demonstrated through qualitative and quantitative experiments.

APPLIED INTELLIGENCE (2022)

Article Computer Science, Artificial Intelligence

Neuromorphic Context-Dependent Learning Framework With Fault-Tolerant Spike Routing

Shuangming Yang et al.

Summary: This study introduces a scalable hardware framework for fault-tolerant context-dependent learning in neuromorphic computing, demonstrating an improvement in network throughput. The proposed system can be utilized for real-time decision-making, brain-machine integration, and research on brain cognition during learning.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022)

Article Computer Science, Artificial Intelligence

CerebelluMorphic: Large-Scale Neuromorphic Model and Architecture for Supervised Motor Learning

Shuangming Yang et al.

Summary: This article introduces a large-scale cerebellar network model and a cerebellum-inspired neuromorphic architecture, demonstrating improved biomimicry. Experimental results show that real-time operation can be achieved, with system throughput up to 4.70 times larger than previous works.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022)

Article Computer Science, Artificial Intelligence

Neural Granger Causality

Alex Tank et al.

Summary: By using structured MLPs and RNNs with sparsity-inducing penalties on weights, we can extract the Granger causal structure and efficiently capture long-range dependencies. Our neural Granger causality methods outperform state-of-the-art nonlinear methods on challenging datasets, demonstrating the utility of deep learning beyond large dataset prediction scenarios.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Article Computer Science, Artificial Intelligence

Mining hidden non-redundant causal relationships in online social networks

Wei Chen et al.

NEURAL COMPUTING & APPLICATIONS (2020)

Article Computer Science, Artificial Intelligence

Scalable Digital Neuromorphic Architecture for Large-Scale Biophysically Meaningful Neural Network With Multi-Compartment Neurons

Shuangming Yang et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2020)

Article Multidisciplinary Sciences

Detecting and quantifying causal associations in large nonlinear time series datasets

Jakob Runge et al.

SCIENCE ADVANCES (2019)

Article Computer Science, Artificial Intelligence

Causal Discovery with Attention-Based Convolutional Neural Networks

Meike Nauta et al.

MACHINE LEARNING AND KNOWLEDGE EXTRACTION (2019)

Article Physics, Multidisciplinary

Efficient digital implementation of a conductance-based globus pallidus neuron and the dynamics analysis

Shuangming Yang et al.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2018)

Article Economics

Testing for Granger causality with mixed frequency data

Eric Ghysels et al.

JOURNAL OF ECONOMETRICS (2016)

Review Statistics & Probability

Causal inference by using invariant prediction: identification and confidence intervals

Jonas Peters et al.

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY (2016)

Article Computer Science, Artificial Intelligence

Cost-efficient FPGA implementation of basal ganglia and their Parkinsonian analysis

Shuangming Yang et al.

NEURAL NETWORKS (2015)

Article Automation & Control Systems

Direct Causality Detection via the Transfer Entropy Approach

Ping Duan et al.

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY (2013)