How expectation and attention influence response speed and memory

People process lots of information about the environment while adapting as this information changes—without high energy use.
IEEE

Analyzing the Semantic Structure of Network Flow: A Threat Detection Method With Independent Generalization Capabilities

Abstract: Network threat detection and identification remain fundamental tasks in cyberspace defence. Existing graph-based detection methods exhibit limited capabilities in transformability and ...
GitHub

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

The paper revisits the prevailing narrative that "SFT memorizes, RL generalizes", mainly focusing on reasoning SFT (with long-CoT supervision). Our core conclusion is that generalization in reasoning ...
IEEE

Delay Synchronization of Drive-Response Boolean Networks and Boolean Control Networks

Abstract: This article investigates the delay synchronization of drive Boolean network (DBN) and response BN (RBN) [response Boolean control network (RBCN)]. Synchronization and time delay are two ...
Journal of Medical Internet Research

Game Addiction Scale Assessment Through a Nationally Representative Sample of Young Adult Men: Item Response Theory Graded–Response Modeling

Whether this scale satisfies the necessary conditions for consideration by item response theory (IRT) modeling remains unknown. However, the Diagnostic and Statistical Manual of Mental Disorders, 5th ...
GitHub

A Reinforcement Learning Perspective with

We are grateful for the many thoughtful comments and feedback from the community regarding DFT, ranging from discussions of related ideas to reports of its application in different scenarios. We have ...
C&EN

Research on the Strong Generalization of Coal Gangue Recognition Technology Based on the Image and Convolutional Neural Network under Complex Conditions

Article subjects are automatically applied from the ACS Subject Taxonomy and describe the scientific concepts and themes of the article. From the above analysis, it can be seen that the image-based ...
PNAS

Curriculum learning for human compositional generalization

In novel situations, people need to repurpose past knowledge to guide behavior (generalization). How they do this remains a mystery in cognitive science. Moreover, building machines that can achieve ...