paper-with-me

홈 › Papers

Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network

2017-02-21 · Aditya Gilra, Wulfram Gerstner

Brains need to predict how the body reacts to motor commands. It is an open question how networks of spiking neurons can learn to reproduce the non-linear body dynamics caused by motor commands, using local, online and stable learning rules. Here, we present a supervised learning scheme for the feedforward and recurrent connections in a network of heterogeneous spiking neurons. The error in the output is fed back through fixed random connections with a negative gain, causing the network to follow the desired dynamics, while an online and local rule changes the weights. The rule for Feedback-based Online Local Learning Of Weights (FOLLOW) is local in the sense that weight changes depend on the presynaptic activity and the error signal projected onto the postsynaptic neuron. We provide examples of learning linear, non-linear and chaotic dynamics, as well as the dynamics of a two-link arm. Using the Lyapunov method, and under reasonable assumptions and approximations, we show that FOLLOW learning is stable uniformly, with the error going to zero asymptotically.

📄 PDF Abstract BibTeX arXiv:1702.06463

Code (0)

등록된 구현이 없습니다.

Tasks

Open-Ended Question Answering

Similar Papers 제목 키워드 기반

Local Dynamics in Trained Recurrent Neural Networks

2016-07-13

Learning a task induces connectivity changes in neural circuits, thereby changing their dynamics. To elucidate task related neural dynamics we study trained Recurrent Neural Networks. We develop a Mean Field Theory for R…

Inferring, Predicting, and Denoising Causal Wave Dynamics

2020-09-19 · Matthias Karlbauer, Sebastian Otte, Hendrik P. A. Lensch, Thomas Scholten 외

The novel DISTributed Artificial neural Network Architecture (DISTANA) is a generative, recurrent graph convolution neural network. It implements a grid or mesh of locally parameterizable laterally connected network modu…

Denoising

Stable fixed points of combinatorial threshold-linear networks

2019-08-27 · Carina Curto, Jesse Geneson, Katherine Morrison

Combinatorial threshold-linear networks (CTLNs) are a special class of recurrent neural networks whose dynamics are tightly controlled by an underlying directed graph. Recurrent networks have long been used as models for…

Non-linear motor control by local learning in spiking neural networks

2017-12-29 · ICML 2018 7 · Aditya Gilra, Wulfram Gerstner

Learning weights in a spiking neural network with hidden neurons, using local, stable and online rules, to control non-linear body dynamics is an open problem. Here, we employ a supervised scheme, Feedback-based Online L…

Convex Programming for Estimation in Nonlinear Recurrent Models

2019-08-26 · Sohail Bahmani, Justin Romberg

We propose a formulation for nonlinear recurrent models that includes simple parametric models of recurrent neural networks as a special case. The proposed formulation leads to a natural estimator in the form of a convex…