Complexity Control Methods of Chaos Dynamics in Recurrent Neural Networks
نویسندگان
چکیده
منابع مشابه
Complexity Control Methods of Dynamics in Recurrent Neural Networks
The paper demonstrates that a complexity of dynamics in recurrent networks with N neurons can be controlled by our gradient methods. The complexity, i.e. the Lyapunov exponent, is calculated by observing the state transition for a long-term period T. One of the control methods is based on the conventional learning algorithms for the recurrent networks. This is the method with high-precision, bu...
متن کاملHarnessing Chaos in Recurrent Neural Networks
In this issue of Neuron, Sussillo and Abbott describe a new learning rule that helps harness the computational power of recurrent neural networks.
متن کاملEnergy Complexity of Recurrent Neural Networks
Recently a new so-called energy complexity measure has been introduced and studied for feedforward perceptron networks. This measure is inspired by the fact that biological neurons require more energy to transmit a spike than not to fire, and the activity of neurons in the brain is quite sparse, with only about 1% of neurons firing. In this letter, we investigate the energy complexity of recurr...
متن کاملArchitectural Complexity Measures of Recurrent Neural Networks
In this paper, we systematically analyse the connecting architectures of recurrent neural networks (RNNs). Our main contribution is twofold: first, we present a rigorous graphtheoretic framework describing the connecting architectures of RNNs in general. Second, we propose three architecture complexity measures of RNNs: (a) the recurrent depth, which captures the RNN’s over-time nonlinear compl...
متن کاملStimulus-dependent suppression of chaos in recurrent neural networks.
Neuronal activity arises from an interaction between ongoing firing generated spontaneously by neural circuits and responses driven by external stimuli. Using mean-field analysis, we ask how a neural network that intrinsically generates chaotic patterns of activity can remain sensitive to extrinsic input. We find that inputs not only drive network responses, but they also actively suppress ongo...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Transactions of the Society of Instrument and Control Engineers
سال: 2001
ISSN: 0453-4654
DOI: 10.9746/sicetr1965.37.250