PloS one
Oct 6, 2025
Maximizing information transfer across different structural scales is critical for effective molecular representation learning. Current molecular graph neural networks fail to fully capture the multi-scale nature of molecular geometry, leading to sub...
Science robotics
Aug 20, 2025
Animals leverage their full embodiment to achieve multimodal, redundant, and subtle communication. To achieve the same for robots, they must similarly exploit their brain-body-environment interactions or their embodied intelligence. To advance this a...
Neural networks : the official journal of the International Neural Network Society
Mar 24, 2025
With the advancement of deep learning, a variety of differential causal discovery methods have emerged, inevitably attracting more attention for their excellent scalability and interpretability. However, these methods often struggle with complex hete...
Physics of life reviews
Mar 21, 2025
The body morphology plays an important role in the way information is perceived and processed by an agent. We address an information theory (IT) account on how the precision of sensors, the accuracy of motors, their placement, the body geometry, shap...
IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society
Mar 18, 2025
The visual sensory organ (VSO) serves as the primary channel for transmitting external information to the brain; therefore, damage to the VSO can severely limit daily activities. Visual-to-Auditory Sensory Substitution (V2A-SS), an innovative approac...
Proceedings of the National Academy of Sciences of the United States of America
Mar 5, 2025
Despite the impressive performance of biological and artificial networks, an intuitive understanding of how their local learning dynamics contribute to network-level task solutions remains a challenge to this date. Efforts to bring learning to a more...
International journal of neural systems
Jul 17, 2024
Recently, Graph Neural Networks (GNNs) have gained widespread application in automatic brain network classification tasks, owing to their ability to directly capture crucial information in non-Euclidean structures. However, two primary challenges per...
IEEE transactions on neural networks and learning systems
Nov 30, 2022
We review the current literature concerned with information plane (IP) analyses of neural network (NN) classifiers. While the underlying information bottleneck theory and the claim that information-theoretic compression is causally linked to generali...
IEEE transactions on neural networks and learning systems
Nov 30, 2022
In this work, we investigate the use of three information-theoretic quantities-entropy, mutual information with the class variable, and a class selectivity measure based on Kullback-Leibler (KL) divergence-to understand and study the behavior of alre...
Sensors (Basel, Switzerland)
Nov 10, 2022
Recent work has shown that deep neural networks are vulnerable to backdoor attacks. In comparison with the success of backdoor-attack methods, existing backdoor-defense methods face a lack of theoretical foundations and interpretable solutions. Most ...