Multitasking via baseline control in recurrent neural networks.
Multitasking via baseline control in recurrent neural networks.
复制标题
通过循环神经网络中的基线控制进行多任务处理。
DOI：
10.1073/pnas.2304394120
复制
发表时间：
2023
影响因子：
11.1
通讯作者：
Mazzucato,Luca
中科院分区：
文献类型：
--
作者：
Ogawa,Shun;Fumarola,Francesco;Mazzucato,Luca
行为状态的变化，如觉醒和运动，强烈影响感觉区域的神经活动，并且可以建模为调节基线输入电流的平均值和方差的长期预测。这些基线调制的计算优势是什么？我们在一个受大脑启发的储层计算框架中研究了这个问题，在这个框架中，我们将淬灭的基线输入改变为具有随机耦合的循环神经网络。我们发现，基线调制控制着水库网络的动态相位，解锁了大量的网络相位。我们发现了一些双稳态相，表现出定点和混沌、两个定点和弱混沌和强混沌同时共存。我们发现了几种现象，包括噪声驱动的混沌增强和遍历性破坏；神经迟滞，即通过相位边界的转换保留了前一相位的记忆。在每个双稳态阶段，油藏执行不同的二元决策任务。可以通过调整基线输入均值和方差来控制不同任务之间的快速切换。此外，我们发现水库网络在任何一阶相边界上都具有最优的记忆性能。总之，基线控制可以在不优化网络耦合的情况下实现多任务处理，为大脑启发的人工智能开辟了方向，并为无处不在的观察到的皮层活动的行为调节提供了解释。
Changes in behavioral state, such as arousal and movements, strongly affect neural activity in sensory areas, and can be modeled as long-range projections regulating the mean and variance of baseline input currents. What are the computational benefits of these baseline modulations? We investigate this question within a brain-inspired framework for reservoir computing, where we vary the quenched baseline inputs to a recurrent neural network with random couplings. We found that baseline modulations control the dynamical phase of the reservoir network, unlocking a vast repertoire of network phases. We uncovered a number of bistable phases exhibiting the simultaneous coexistence of fixed points and chaos, of two fixed points, and of weak and strong chaos. We identified several phenomena, including noise-driven enhancement of chaos and ergodicity breaking; neural hysteresis, whereby transitions across a phase boundary retain the memory of the preceding phase. In each bistable phase, the reservoir performs a different binary decision-making task. Fast switching between different tasks can be controlled by adjusting the baseline input mean and variance. Moreover, we found that the reservoir network achieves optimal memory performance at any first-order phase boundary. In summary, baseline control enables multitasking without any optimization of the network couplings, opening directions for brain-inspired artificial intelligence and providing an interpretation for the ubiquitously observed behavioral modulations of cortical activity.