Learning in memristive neural network architectures using analog backpropagation circuits
O Krestinskaya, KN Salama… - IEEE Transactions on …, 2018 - ieeexplore.ieee.org
The on-chip implementation of learning algorithms would speed up the training of neural
networks in crossbar arrays. The circuit level design and implementation of a back …
networks in crossbar arrays. The circuit level design and implementation of a back …
Sequential attractors in combinatorial threshold-linear networks
Sequences of neural activity arise in many brain areas, including cortex, hippocampus, and
central pattern generator circuits that underlie rhythmic behaviors like locomotion. While …
central pattern generator circuits that underlie rhythmic behaviors like locomotion. While …
[HTML][HTML] Learning recurrent dynamics in spiking networks
Spiking activity of neurons engaged in learning and performing a task show complex
spatiotemporal dynamics. While the output of recurrent network models can learn to perform …
spatiotemporal dynamics. While the output of recurrent network models can learn to perform …
[HTML][HTML] Core motifs predict dynamic attractors in combinatorial threshold-linear networks
C Parmelee, S Moore, K Morrison, C Curto - PloS one, 2022 - journals.plos.org
Combinatorial threshold-linear networks (CTLNs) are a special class of inhibition-dominated
TLNs defined from directed graphs. Like more general TLNs, they display a wide variety of …
TLNs defined from directed graphs. Like more general TLNs, they display a wide variety of …
Fixed points of competitive threshold-linear networks
Threshold-linear networks (TLNs) are models of neural networks that consist of simple,
perceptron-like neurons and exhibit nonlinear dynamics determined by the network's …
perceptron-like neurons and exhibit nonlinear dynamics determined by the network's …
Oscillatory networks: Insights from piecewise-linear modeling
There is enormous interest--both mathematically and in diverse applications--in
understanding the dynamics of coupled oscillator networks. The real-world motivation of …
understanding the dynamics of coupled oscillator networks. The real-world motivation of …
Diversity of emergent dynamics in competitive threshold-linear networks
Threshold-linear networks consist of simple units interacting in the presence of a threshold
nonlinearity. Competitive threshold-linear networks have long been known to exhibit …
nonlinearity. Competitive threshold-linear networks have long been known to exhibit …
Pattern completion in symmetric threshold-linear networks
C Curto, K Morrison - Neural computation, 2016 - ieeexplore.ieee.org
Threshold-linear networks are a common class of firing rate models that describe recurrent
interactions among neurons. Unlike their linear counterparts, these networks generically …
interactions among neurons. Unlike their linear counterparts, these networks generically …
Periodic solutions in threshold-linear networks and their entrainment
Threshold-linear networks (TLNs) are recurrent networks where the dynamics are threshold-
linear (linearly rectified at zero). Mathematically, they consist of coupled nonsmooth ordinary …
linear (linearly rectified at zero). Mathematically, they consist of coupled nonsmooth ordinary …
Diversity of emergent dynamics in competitive threshold-linear networks
Threshold-linear networks consist of simple units interacting in the presence of a threshold
nonlinearity. Competitive threshold-linear networks have long been known to exhibit …
nonlinearity. Competitive threshold-linear networks have long been known to exhibit …