Neural and Evolutionary Computing
PulseAugur coverage of Neural and Evolutionary Computing — every cluster mentioning Neural and Evolutionary Computing across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Research explores inherited learning benefits in artificial ecologies
A new research paper explores the concept of inherited learning within artificial populations, examining how controls and update allocation influence collective benefits. The study, conducted in a resource-limited artif…
-
Research paper questions memory retention in evolutionary algorithms
A new research paper titled "What Makes a Redundant Representation Remember? Lineage Isolation, Not Masking" explores the effectiveness of memory-based evolutionary algorithms in dynamic optimization. The study reveals …
-
LLM framework SHA-PF optimizes engineering design formulations for efficient search
Researchers have developed SHA-PF, a new framework that uses Large Language Models (LLMs) to formulate engineering design problems. Unlike previous methods that focused solely on aligning formulations with design intent…
-
Reinforcement learning models need to account for biological variability
A new paper proposes a significant shift in how reinforcement learning (RL) is applied to biological research. While RL has been effective in explaining biological behavior, it typically models only the average or optim…
-
New research explores social-spatial dependencies in AI navigation
Researchers have developed a new approach to understanding visual navigation by examining the social-spatial dependencies in group behavior. Their study trained individual neural network agents to navigate in various so…
-
Survey paper details biologically plausible neural system models
A new survey paper published on arXiv details various approaches to mathematically modeling biologically plausible neural systems. The paper categorizes and characterizes these models based on shared features and specif…
-
New method generates sparse recurrent networks inspired by biological development
Researchers have developed a method to generate sparse recurrent neural networks by drawing inspiration from biological development. Using hypernetworks, they created a compressed generative process that produces the co…