Short-term plasticity in a liquid state machine biomimetic robot arm controller

Azambuja, Ricardo de; Klein, Frederico Belmonte; Adams, Samantha V.; Stoelen, Martin F.; Cangelosi, Angelo

doi:10.1109/ijcnn.2017.7966283

Cited by 12 publications

(5 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It uses calcium concentration, c for depicting the activity of the neuron in the classifier to enable selective weight change during a training phase. The calcium concentration for a neuron is defined by a first order equation (6) with timescale τ c . Steady state concentration c s is approximately given by (7) and is the indicator of spike rate (f r ) of the neuron.…”

Section: Classifiermentioning

confidence: 99%

Predicting Performance using Approximate State Space Model for Liquid State Machines

Gorad

Saraswat

Ganguly

2019

2019 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Liquid State Machine (LSM) is a brain-inspired architecture used for solving problems like speech recognition and time series prediction. LSM comprises of a randomly connected recurrent network of spiking neurons. This network propagates the non-linear neuronal and synaptic dynamics. Maass et al. have argued that the non-linear dynamics of LSMs is essential for its performance as a universal computer. Lyapunov exponent (µ), used to characterize the non-linearity of the network, correlates well with LSM performance. We propose a complementary approach of approximating the LSM dynamics with a linear state space representation. The spike rates from this model are well correlated to the spike rates from LSM. Such equivalence allows the extraction of a memory metric (τM ) from the state transition matrix. τM displays high correlation with performance. Further, high τM system require lesser epochs to achieve a given accuracy. Being computationally cheap (1800× time efficient compared to LSM), the τM metric enables exploration of the vast parameter design space. We observe that the performance correlation of the τM surpasses the Lyapunov exponent (µ), (2 − 4× improvement) in the high-performance regime over multiple datasets. In fact, while µ increases monotonically with network activity, the performance reaches a maxima at a specific activity described in literature as the edge of chaos. On the other hand, τM remains correlated with LSM performance even as µ increases monotonically. Hence, τM captures the useful memory of network activity that enables LSM performance. It also enables rapid design space exploration and fine-tuning of LSM parameters for high performance.

show abstract

Section: Classifiermentioning

confidence: 99%

Predicting Performance using Approximate State Space Model for Liquid State Machines

Gorad

Saraswat

Ganguly

2019

2019 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…SMPs expand SHCs into a stable, learnable system with a clear transformation from state space into a robot's task space. Mathematical representations of biological systems are commonly used to develop robot control frameworks [8,18,24,40,45,46]. These frameworks have value in both biological and engineering applications, and characterizing their parameters increases ease-of-use in either application [47][48][49].…”

Section: Relevant Workmentioning

confidence: 99%

Stable Heteroclinic Channel-Based Movement Primitives: Tuning Trajectories Using Saddle Parameters

Rouse,

Daltorio

2024

Applied Sciences

View full text Add to dashboard Cite

Dynamic systems which underlie controlled systems are expected to increase in complexity as robots, devices, and connected networks become more intelligent. While classical stable systems converge to a stable point (a sink), another type of stability is to consider a stable path rather than a single point. Such stable paths can be made of saddle points that draw in trajectories from certain regions, and then push the trajectory toward the next saddle point. These chains of saddles are called stable heteroclinic channels (SHCs) and can be used in robotic control to represent time sequences. While we have previously shown that each saddle is visualizable as a trajectory waypoint in phase space, how to increase the fidelity of the trajectory was unclear. In this paper, we hypothesized that the waypoints can be individually modified to locally vary fidelity. Specifically, we expected that increasing the saddle value (ratio of saddle eigenvalues) causes the trajectory to slow to more closely approach a particular saddle. Combined with other parameters that control speed and magnitude, a system expressed with an SHC can be modified locally, point by point, without disrupting the rest of the path, supporting their use in motion primitives. While some combinations can enable a trajectory to better reach into corners, other combinations can rotate, distort, and round the trajectory surrounding the modified saddle. Of the system parameters, the saddle value provides the most predictable tunability across 3 orders of magnitude.

show abstract

“…Other approaches to the problem use Liquid State Machines with 'dynamic synapses' [49]. The aim is to give the system 'short-term plasticity', a possibility already described in [5].…”

Section: B Drawing and Motionmentioning

confidence: 99%

Reservoir Computing in robotics: a review

Baldini¹

2022

Preprint

View full text Add to dashboard Cite

Reservoir Computing is a relatively new framework created to allow the usage of powerful but complex systems as computational mediums. The basic approach consists in training only a readout layer, exploiting the innate separation and transformation provided by the previous, untrained system. This approach has shown to possess great computational capabilities and is successfully used to achieve many tasks. This review aims to represent the current 'state-of-the-art' of the usage of Reservoir Computing techniques in the robotic field. An introductory description of the framework and its implementations is initially given. Subsequently, a summary of interesting applications, approaches, and solutions is presented and discussed. Considerations, ideas and possible future developments are proposed in the explanation.

show abstract

Short-term plasticity in a liquid state machine biomimetic robot arm controller

Cited by 12 publications

References 43 publications

Predicting Performance using Approximate State Space Model for Liquid State Machines

Predicting Performance using Approximate State Space Model for Liquid State Machines

Stable Heteroclinic Channel-Based Movement Primitives: Tuning Trajectories Using Saddle Parameters

Reservoir Computing in robotics: a review

Contact Info

Product

Resources

About