Rich and lazy learning of task representations in brains and neural networks
Rich and lazy learning of task representations in brains and neural networks
复制标题
大脑和神经网络中任务表征的丰富而惰性的学习
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
C. Summerfield
中科院分区：
文献类型：
--
作者：
Timo Flesch;Keno Juechems;T. Dumbalska;Andrew M. Saxe;C. Summerfield
神经群体如何对多个潜在冲突的任务进行编码？在这里，我们使用了涉及神经网络的计算模拟来定义这个多任务问题的“懒惰”和“丰富”编码解决方案，这是在学习速度和健壮性之间的权衡。在懒惰学习过程中，输入维度通过随机投影扩展到网络隐含层，而在丰富学习中，隐藏单元获得的结构化表示优先于不相关的特征。对于上下文相关的决策，一个丰富的解决方案是将任务表示投影到低维和正交流形上。利用人类的行为测试和神经成像，以及对猕猴前额叶皮质神经信号的分析，我们报告了生物大脑中神经编码模式的证据，其维度和神经几何与丰富的学习机制一致。
How do neural populations code for multiple, potentially conflicting tasks? Here, we used computational simulations involving neural networks to define “lazy” and “rich” coding solutions to this multitasking problem, which trade off learning speed for robustness. During lazy learning the input dimensionality is expanded by random projections to the network hidden layer, whereas in rich learning hidden units acquire structured representations that privilege relevant over irrelevant features. For context-dependent decision-making, one rich solution is to project task representations onto low-dimensional and orthogonal manifolds. Using behavioural testing and neuroimaging in humans, and analysis of neural signals from macaque prefrontal cortex, we report evidence for neural coding patterns in biological brains whose dimensionality and neural geometry are consistent with the rich learning regime.
影响因子：
3.7
作者：
Cole, Michael W.;Ito, Takuya;Braver, Todd S.
通讯作者：
Braver, Todd S.
影响因子：
5.7
作者：
Saxena, Shreya;Cunningham, John P.
通讯作者：
Cunningham, John P.