paper-with-me

홈 › Papers

Dynamic Adaptive Computation: Tuning network states to task requirements

2018-09-20

Neural circuits are able to perform computations under very diverse conditions and requirements. The required computations impose clear constraints on their fine-tuning: a rapid and maximally informative response to stimuli in general requires decorrelated baseline neural activity. Such network dynamics is known as asynchronous-irregular. In contrast, spatio-temporal integration of information requires maintenance and transfer of stimulus information over extended time periods. This can be realized at criticality, a phase transition where correlations, sensitivity and integration time diverge. Being able to flexibly switch, or even combine the above properties in a task-dependent manner would present a clear functional advantage. We propose that cortex operates in a "reverberating regime" because it is particularly favorable for ready adaptation of computational properties to context and task. This reverberating regime enables cortical networks to interpolate between the asynchronous-irregular and the critical state by small changes in effective synaptic strength or excitation-inhibition ratio. These changes directly adapt computational properties, including sensitivity, amplification, integration time and correlation length within the local network. We review recent converging evidence that cortex in vivo operates in the reverberating regime, and that various cortical areas have adapted their integration times to processing requirements. In addition, we propose that neuromodulation enables a fine-tuning of the network, so that local circuits can either decorrelate or integrate, and quench or maintain their input depending on task. We argue that this task-dependent tuning, which we call "dynamic adaptive computation", presents a central organization principle of cortical networks and discuss first experimental evidence.

📄 PDF Abstract BibTeX arXiv:1809.07550

Code (0)

등록된 구현이 없습니다.

Tasks

Sensitivity

Similar Papers 제목 키워드 기반

System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts

2025-05-25 · Xiaoqiang Wang, Suyuchen Wang, Yun Zhu, Bang Liu

Chain-of-thought (CoT) reasoning enables large language models (LLMs) to move beyond fast System-1 responses and engage in deliberative System-2 reasoning. However, this comes at the cost of significant inefficiency due …

GSM8K

Layer Flexible Adaptive Computational Time

2018-12-06 · Lida Zhang, Abdolghani Ebrahimi, Diego Klabjan

Deep recurrent neural networks perform well on sequence data and are the model of choice. However, it is a daunting task to decide the structure of the networks, i.e. the number of layers, especially considering differen…

Language ModelingLanguage Modelling

RoSA: Enhancing Parameter-Efficient Fine-Tuning via RoPE-aware Selective Adaptation in Large Language Models

2025-11-21 · Dayan Pan, Jingyuan Wang, Yilong Zhou, Jiawei Cheng 외 arxiv

Fine-tuning large language models is essential for task-specific adaptation, yet it remains computationally prohibitive. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a solution, but current approaches t…

parameter-efficient fine-tuning

Layer Flexible Adaptive Computation Time for Recurrent Neural Networks

2019-09-25 · Lida Zhang, Diego Klabjan

Deep recurrent neural networks perform well on sequence data and are the model of choice. However, it is a daunting task to decide the structure of the networks, i.e. the number of layers, especially considering differen…

Language ModelingLanguage Modelling

AdaRankGrad: Adaptive Gradient-Rank and Moments for Memory-Efficient LLMs Training and Fine-Tuning

2024-10-23 · Yehonathan Refael, Jonathan Svirsky, Boris Shustin, Wasim Huleihel 외

Training and fine-tuning large language models (LLMs) come with challenges related to memory and computational requirements due to the increasing size of the model weights and the optimizer states. Various techniques hav…