Learning Association
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Learning Association via Track-Detection Matching for Multi-Object Tracking
arXiv:2512.22105v2 Announce Type: replace Abstract: Multi-object tracking aims to maintain object identities over time by associating detections across video frames. Two dominant paradigms exist in literature: tracking-by-detection methods, which are computationally efficient but rely on handcrafted association heuristics, and end-to-end approaches, which learn association from data at the cost of higher computational complexity. We propose Track-Detection Link Prediction (TDLP), a...
Characterizing Students' LLM Usage Behaviors and Their Association with Learning in Critical Thinking Tasks
Announce Type: replace Abstract: Large language models (LLMs) are becoming increasingly embedded in students' learning practices, yet much of what is known about how students use LLMs and how this usage impacts learning comes from problem-solving domains or constrained experimental settings. We present an analysis of data on LLM usage collected during two offerings of a research-oriented course where students learn to read, reason about, and critique academic papers. Without restrictions on...
Muon in Associative Memory Learning: Training Dynamics and Scaling Laws
arXiv:2602.05725v3 Announce Type: replace Abstract: Muon updates matrix parameters via the matrix sign of the gradient and has shown strong empirical gains, yet its dynamics and scaling behavior remain unclear in theory. We study Muon in a linear associative memory model with softmax retrieval and a hierarchical frequency spectrum over query-answer pairs, with and without label noise. In this setting, we show that Gradient Descent (GD) learns frequency components at highly imbalanced rates,...
Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning
arXiv:2606.09289v1 Announce Type: new Abstract: Understanding tactical organisation of association football, hereafter referred to as football, requires identifying distinct match phases. Yet in-possession phases are rarely directly observable and are shaped by evolving tactical intentions, rather than spatial patterns alone. This study proposes a data-driven framework for identifying in-possession match phases from spatiotemporal tracking data.
Hippocampal CA2 modulates trace fear conditioning through circuit-specific control of CA1
Forming associations between temporally separated events depends on pathways linking the CA1, the subiculum (SUB), and the entorhinal cortex. The degree to which this process requires the CA2, which shares extensive connectivity with these regions, remains unknown. conditioning (TFC), where mice learn to associate a tone and shock separated by a temporal gap, we showed that the dCA2 contributes to TFC.
Emergence of social recognition in auditory and integrative circuits during pair bonding
Social relationships profoundly shape the perception of communication signals. In animals that form long-term social bonds, sensory cues such as vocalizations, scent, or physical appearance, and rewarding mating experiences can become associated with a bonded mate. While this natural process has hallmarks of some forms of associative learning, little is known about where or how these experiences shape neural circuits over the course of pair bonding.
Rationality Measurement and Theory for Reinforcement Learning Agents
Announce Type: replace Abstract: This paper proposes a suite of rationality measures and associated theory for reinforcement learning agents, a property increasingly critical yet rarely explored. We define an action in deployment to be perfectly rational if it maximises the hidden true value function in the steepest direction. The expected value discrepancy of a policy's actions against their rational counterparts, culminating over the trajectory in deployment, is defined to be expected...
Robust learning-driven structural and functional plasticity of spines in the mature mouse cortex
Spines in the adult cortex are thought to be highly stable, and that their capacity for modest remodeling supports learning. Using a visual association task and a multilevel imaging approach in adult mice, we found a robust learning-driven increase in the complexity of spine nanostructure, as well as a rapid and persistent increase in spine formation during task acquisition that were accompanied by an overall reduction in spine size of layer 2/3 neurons in the primary visual cortex (V1)....
Spontaneous and stimulus-driven arousal produce distinct acetylcholine dynamics across sensory and prefrontal cortex
Acetylcholine (ACh) release from the basal forebrain has traditionally been viewed as a slow, spatially diffuse signal regulating cortical arousal across sleep and wakefulness. Recent characterizations with higher resolution optical sensors have revealed rapid, local cholinergic modulation supporting dynamic changes in sensory processing, associative learning, and behavioral state. However, sensory events that recruit cortical ACh often also change arousal and evoke movements, making it...
Pretraining Recurrent Networks without Recurrence
arXiv:2606.06479v1 Announce Type: new Abstract: Training recurrent neural networks (RNNs) requires assigning credit across long sequences of computations. Standard backpropagation through time (BPTT) addresses this problem poorly: it is sequential in time, limiting parallelism, and suffers from vanishing or exploding gradients, making long-range associations difficult to learn. We propose Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit...