Pattern Recognition in a Bucket

By Chrisantha Fernando, Sampsa Sojakka. European Conference on Artificial Life, 2003

309 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Information processing via physical soft body (2015, methodology): “A number of different implementations for reservoirs have been proposed, such as abstract dynamical systems for echo state networks 7,8 or models of neurons for liquid state machines 9 , the surface of water in a laminar state 14 , and nonlinear mass spring systems 15–19 .”
Reservoir Computing Trends (2012, background): “Potential and functioning examples include analog electronics [40,39], randomly crystallized nonlinear electronic networks [44], opto-electronic [26,36] and optical [47] systems, or just a bucket filled with water [12].”
Reservoir computing approaches to recurrent neural network training (2009, background): “idea quite literally) by feeding the input via mechanical actuators into a reservoir full of water, recording the state of its surface optically, and successfully training a readout multilayer perceptron on several classification tasks [57].”
An overview of reservoir computing: theory, applications and implementations (2007, background): “Examples of this are the use of a real bucket of water as reservoir to do speech recognition [8], the genetic regulatory network in a cell [7, 23] and using the actual brain of a cat [32].”
Recent Advances in Physical Reservoir Computing: A Review (2018, unknown): “2 (Fernando & Sojakka, 2003).”