Neural Change Prediction
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Neural Change Prediction: Relating Software Changes to Their Effects and Vice Versa
Announce Type: new Abstract: Much of software development revolves around understanding the relationship between software changes and their effects. If we could learn and predict those relationships, such predictions could benefit several areas of software engineering. While recent advances in artificial intelligence have shown great promise in software engineering tasks, predicting the semantics of code without executing it remains a big challenge.
Structure and Scale in Simplicial Sequence Modelling
arXiv:2606.01302v1 Announce Type: new Abstract: Modern large-scale deep learning exhibits two striking empirical phenomena: behavioural scaling laws (predictable performance gains with increasing scale) and emergent mechanisms (structured internal representations and circuits in deep neural networks). We hypothesise that these two phenomena are connected: that predictable changes in behaviour are the result of predictable changes in internal computational structure.
Deep learning four decades of human migration
Abstract Human migration is a fundamental driver of global demographic change, shaping population structure, labour markets and social policy across countries1,2,3. Although long-term migration patterns are often linked to economic development4, they can shift rapidly in response to shocks such as conflict, environmental crises and political change5. Despite its importance, migration remains difficult to measure consistently: existing data are sparse, concentrated in high-income settings and...
From Prediction to Self: Developmental Conditions for Agency in Minimal Neural Systems
arXiv:2606.05605v1 Announce Type: new Abstract: How does a system that merely predicts the world come to distinguish its own causal influence from everything else? We trace this transition in a minimal 192-dimensional GRU through 40 controlled experiments arranged as a developmental sequence, adding components one at a time and tracking whether the system can distinguish self-caused from world-caused changes. The developmental path reveals four conditions that must be satisfied in strict...
Neuron Populations Exhibit Divergent Selectivity with Scale
Announce Type: new Abstract: We investigate whether neuron populations within neural networks evolve predictably with scale, extending scaling laws beyond macroscopic observables such as loss. To probe this question, we study Rosetta Neurons, a previously characterized class of neurons whose activation patterns are similar across independently trained models (Dravid et al., 2023). In separate analyses of language models up to 30B parameters and vision models up to 5B parameters, we observe...
SpliceBind: Isoform-Aware Prediction of Binding Pocket Druggability
arXiv:2606.04020v1 Announce Type: cross Abstract: Splice-mediated drug resistance occurs in up to 40% of patients on targeted kinase inhibitors, yet state-of-the-art druggability tools operate on single structures and cannot compare across isoforms. We introduce SpliceBind, a graph neural network framework for isoform-aware druggability prediction. Beyond improving prediction accuracy (AUROC 0.703 vs. P2Rank 0.634, p = 0.026), we address a more fundamental question: when do structural...
A Hypertoroidal Covering for Perfect Color Equivariance
arXiv:2603.04256v3 Announce Type: replace Abstract: When the color distribution of input images changes at inference, the performance of conventional neural network architectures drops considerably. A few researchers have begun to incorporate prior knowledge of color geometry in neural network design. These color equivariant architectures have modeled hue variation with 2D rotations, and saturation and luminance transformations as 1D translations.
A Geometric Measure of Linear Separability for Neural Representations
Announce Type: new Abstract: Modern neural classifiers commonly rely on linear readouts, yet predictive metrics alone do not characterize the class-wise geometry of the representations on which such readouts operate. We introduce the directional linear separability measure (LSM), a finite-sample diagnostic for one-sided affine separability. For a target class A and a competing set B, LSM searches over affine halfspaces that contain all samples in A and measures the smallest competing-sample...
Your brain starts making social decisions before you do
Your brain starts making social decisions before you do - Date: - June 2, 2026 - Source: - The Hebrew University of Jerusalem - Summary: - Researchers found that social behavior begins in the brain before it becomes visible as movement. In zebrafish, a coordinated pattern of activity spread across the brain several seconds before the animals approached another fish. A higher brain region called the pallium played a key role, and fish with stronger neural signals were generally more social.
Neural synchrony between prefrontal and visual cortex supports visual working memory
Working memory appears to depend on neural mechanisms that are distributed across the brain. Specifically, neural activity persists in the prefrontal cortex while memories are maintained, and at the same time, the visual contents of memory can be precisely decoded from the patterns of activity in visual cortex. Contemporary models attempt to account for these findings by positing that higher-order areas, like prefrontal cortex, somehow control memory storage by recruiting encoding mechanisms...