6 articles tagged with #neural-dynamics. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers have synthesized geometric and causal analysis approaches to explain how large language models transform context into predictions across layers, identifying a sharp computational transition in decoder-only LLMs and revealing that angular structure in late layers governs token prediction while representation norms operate independently.
Researchers demonstrate that training physical neural networks composed of nonlinear oscillators reveals a fundamental tradeoff: memory capacity, gradient stability, and dynamical expressivity cannot be simultaneously optimized because all three are governed by damping parameters. Empirical validation on a twenty-oscillator network confirms theoretical predictions, showing trained substrates outperform frozen ones only within a narrow optimal band that contracts as memory horizons increase.
Researchers demonstrate that small LSTM neural networks exhibit critical dynamics near optimal training, displaying scale-free avalanche statistics and branching parameters close to unity, while larger models remain subcritical. The study introduces a mixture branching process framework to explain how subcritical dynamics can coexist with long-range temporal correlations, suggesting criticality emerges as a capacity-dependent property in artificial neural networks.
This survey comprehensively maps the evolution of machine learning methods for decoding neural activity, from classical state-space models to modern deep generative approaches. It organizes techniques across three domains—single-region dynamics, multi-region communication, and behavior-aligned modeling—while highlighting emerging foundation models and open challenges in causal inference for brain research.
Researchers introduce CASSM, a Bayesian framework that combines Kalman filtering with model selection to improve neural dynamics modeling on modern datasets. The method addresses computational complexity and uncertainty calibration challenges, offering competitive performance with deep networks while maintaining better uncertainty quantification, particularly for datasets with fewer trials than recorded neurons.
Researchers discovered that continuous-time RNNs trained with noise injected inside activation functions paradoxically perform best when noise remains present at test time, contradicting conventional assumptions about noise removal. This phenomenon stems from noise-induced shifts in neural network dynamics that become computationally integrated into learned representations, revealing that networks can overfit to training noise itself rather than just input-output mappings.
