The Application of Liquid State Machines in Robot Path Planning

  title={The Application of Liquid State Machines in Robot Path Planning},
  author={Yanduo Zhang and Kun Wang},
  journal={J. Comput.},
This paper discusses the Liquid state machines and does some researches on spiking neural network and Parallel Delta Rule, using them to solve the robot path planning optimization problems, at the same time we do simulation by Matlab, the result of the experimental reveal that the LSM can solve these problems effectively. 
Intelligent Reservoir Generation for Liquid State Machines using Evolutionary Optimization
This paper employs the reservoir computing technique and genetic algorithms in order to develop useful networks that can be deployed on neuromorphic hardware and discusses the complexities of determining whether or not to use the genetic algorithms approach for liquid state machine generation. Expand
High-Density Liquid-State Machine Circuitry for Time-Series Forecasting
A new low-cost methodology to implement high-density LSM by using Boolean gates is shown, based on the use of probabilistic computing concepts to reduce hardware requirements, thus considerably increasing the neuron count per chip. Expand
Training the Stochastic Kinetic Model of Neuron for Calculation of an Object’s Position in Space
The trained stochastic kinetic model of neuron is tested in solving the problem of approximation, where for the approximated function the membrane potential obtained using different models of a biological neuron was chosen. Expand
A Digital Liquid State Machine With Biologically Inspired Learning and Its Application to Speech Recognition
The simulation results show that in terms of isolated word recognition evaluated using the TI46 speech corpus, the proposed digital LSM rivals the state-of-the-art hidden Markov-model-based recognizer Sphinx-4 and outperforms all other reported recognizers including the ones that are based upon the LSM or neural networks. Expand
Liquid State Machine With Dendritically Enhanced Readout for Low-Power, Neuromorphic VLSI Implementations
A new neuro-inspired, hardware-friendly readout stage for the liquid state machine (LSM), a popular model for reservoir computing, which can attain better performance with significantly less synaptic resources making it attractive for VLSI implementation. Expand
This study proposes motion learning using spatio temporal neural network based on reward-modulated spike-timing-dependent plasticity (STDP), whereby the learning weight adjustment provided by the standard STDP is modulated by the reinforcement. Expand
Handwritten signatures recognition using Liquid State Machine
This work investigated a recently proposed model 'Liquid State Machine (LSM) using spiking neural network' and its applicability for recognition of the 'handwritten signature problem'. Expand
Key-Threshold based spiking neural network
A novel model of Key-Threshold based Spiking Neural Network (KTSNN) is proposed, which consists of quasi-neurons oriented to recognize any key-spikes distributed in time (sequence of spikes) or in space (in synapses). Expand
Pattern Classification by Spiking Neural Networks Combining Self-Organized and Reward-Related Spike-Timing-Dependent Plasticity
This work studied the ability of a network in which recurrent spiking neural networks are combined with STDP for non-supervised learning, with an output layer joined by DA-STDP for supervised learning, to perform pattern classification and confirmed that this network could performpattern classification using the STDP effect. Expand
Applications of Metaheuristics in Reservoir Computing Techniques: A Review
This review discusses areas where metaheuristics are used in the echo state network—a pioneer in the reservoir computing field and trends and research gaps are discussed. Expand


A Model for Real-Time Computation in Generic Neural Microcircuits
A new computational model is proposed that is based on principles of high dimensional dynamical systems in combination with statistical learning theory and can be implemented on generic evolved or found recurrent circuitry. Expand
Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
A new computational model for real-time computing on time-varying input that provides an alternative to paradigms based on Turing machines or attractor neural networks, based on principles of high-dimensional dynamical systems in combination with statistical learning theory and can be implemented on generic evolved or found recurrent circuitry. Expand
Pattern Recognition in a Bucket
This paper demonstrates that the waves produced on the surface of water can be used as the medium for a “Liquid State Machine” that pre-processes inputs so allowing a simple perceptron to solve theExpand
The''echo state''approach to analysing and training recurrent neural networks
The report introduces a constructive learning algorithm for recurrent neural networks, which modifies only the weights to output units in order to achieve the learning task. key words: recurrentExpand
Pattern recognition in a bucket: a real liquid brain
  • Pattern recognition in a bucket: a real liquid brain
  • 2003
Spiking Neuron Models: Single Neurons, Populations, Plasticity