Live briefing
Everything about Liquid state machine
Type of reservoir computer
A liquid state machine (LSM) is a type of reservoir computer that uses a spiking neural network. An LSM consists of a large collection of units. Each node receives time varying input from external sources as well as from other nodes. Nodes are randomly connected to each other. The recurrent nature of the connections turns the time varying input into a spatio-temporal pattern of activations in the network nodes. The spatio-temporal patterns of activation are read out by linear discriminant units. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Liquid state machineA 5-minute orientation
- Skim a recent paper: LSMCore: A 69k-Synapse/mm 2 Single-Core Digital Neuromorphic Processor for Liquid State MachineInfluential work since 2022
- Pick up a classic book: American FilmThe most-reprinted book on the subject
- Read the landmark paper: Isolated word recognition with the Liquid State Machine: a case studyCited 223 times
- Go sideways: Reservoir computingA closely related topic
- Go sideways: Echo state networkA closely related topic
📖 Definitions
Noun A kind of reservoir computer that uses a spiking neural network with nodes randomly connected to each other.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
Isolated word recognition with the Liquid State Machine: a case study
The cerebellum as a liquid state machine
Liquid State Machine With Dendritically Enhanced Readout for Low-Power, Neuromorphic VLSI Implementations
Effects of synaptic connectivity on liquid state machine performance
Movement prediction from real-world images using a liquid state machine
A neural architecture search based framework for liquid state machine design
Liquid State Machine on SpiNNaker for Spatio-Temporal Classification Tasks
High-Density Liquid-State Machine Circuitry for Time-Series Forecasting
🆕 Influential since 2022
LSMCore: A 69k-Synapse/mm 2 Single-Core Digital Neuromorphic Processor for Liquid State Machine
Resistive memory-based zero-shot liquid state machine for multimodal event data learning
Fault diagnosis using liquid state machine with spiking-timing-dependent plasticity learning rule
Bluetooth Indoor Localization With Gaussian–Bernoulli Restricted Boltzmann Machine Plus Liquid State Machine
Perfecting Liquid-State Theories with Machine Intelligence
📚 Books worth reading
American FilmAmerican Film Institute · 1975
Bulletin of the United States Army Medical DepartmentUnited States. Army Medical Service. · 1944
The little book of the warEva March Tappan · 1918- 📕Financial assets, debt, and liquidity crisesMatthieu Charpe · 2011
Winsor McCayWinsor McCay · 2003
MultimediaRandall Packer, Ken Jordan · 2001
Principles of water treatmentJohn C. Crittenden, Kerry J. Howe · 2012
Treaty Occupationay ToxicologySuelen Queiroz · 2010
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Reservoir computing Reservoir computing is a framework for computation derived from recurrent neural network theory that maps input signals into higher dimensional computational…
- Echo state network An echo state network (ESN) is a type of reservoir computer that uses a recurrent neural network with a sparsely connected hidden layer (with typically…
- Types of artificial neural networks Types of neural networks (NN) include a family of techniques. The simplest types have static components, including number of units, number of layers, unit…
- Winner-take-all (computing) Winner-take-all is a computational principle applied in computational models of neural networks by which neurons compete with each other for activation…
- Spiking neural network Spiking neural networks (SNNs) are artificial neural networks (ANN) that mimic natural neural networks. These models leverage timing of discrete spikes…
- Recurrent neural network In artificial neural networks, recurrent neural networks (RNNs) are designed for processing sequential data, such as text, speech, and time series, where…
- Self-organizing map A self-organizing map (SOM) or self-organizing feature map (SOFM) is an unsupervised machine learning technique used to produce a low-dimensional (typically…
- Linear-nonlinear-Poisson cascade model The linear-nonlinear-Poisson (LNP) cascade model is a simplified functional model of neural spike responses. It has been successfully used to describe…