P2.104 Gait analysis of autistic children with Echo State Networks

Noris, Basilio; Nobile, Maria; Piccini, Luca; Berti, Matteo; Mani, Elisa; Molteni, Massimo; Keller, Flavio; Campolo, Domenico; Billard, Aude

doi:10.1016/s1353-8020(08)70335-3

Cited by 5 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Attempts to automatize the diagnosis Noris et al [140] measured a collection of three-dimensional coordinates from 14 markers applied to the joints of the lower-body area of 22 children (11 children with ASD, 11 controls) using an infrared camera (motion-capture). Using an echo state network (a form of recurrent neural networks -NN) they were able to extract differences in the cycles evolution and could stratify children with ASD and controls with an accuracy of up to 91%.…”

Section: Posture Analysis (N = 10 Table 1)mentioning

confidence: 99%

Automatic Assessment of Motor Impairments in Autism Spectrum Disorders: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

Section: Posture Analysis (N = 10 Table 1)mentioning

confidence: 99%

Automatic Assessment of Motor Impairments in Autism Spectrum Disorders: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

“…In other words, the effects of feeding an input into the network eventually die out. This is only a guideline however, as the optimal spectral radius is task dependent and can be much higher or lower than unity for some datasets [3,7].…”

Section: Reservoir Computingmentioning

confidence: 99%

“…whereW k+1 contains the OLS estimates calculated in Equation 7. For a more rigorous mathematical explanation, see Similä and Tikka [14].…”

Section: Reservoir With Random Static Projectionsmentioning

confidence: 99%

Pruning reservoirs with Random Static Projections

Butcher

Day

Haycock

et al. 2010

2010 IEEE International Workshop on Machine Learning for Signal Processing

View full text Add to dashboard Cite

Reservoir Computing is a relatively new field of Recurrent Neural Networks in which only the output weights are re-calculated by the training process, removing the problems associated with traditional gradient descent algorithms. As the reservoir is recurrent, it can possess short term memory, but there is a trade-off between the amount of memory a reservoir can have and its nonlinear mapping capabilities. A new, custom architecture was recently proposed to overcome this by combining a reservoir with an extreme learning machine to deliver improved results. This paper extends this architecture further by introducing a ranking and pruning algorithm which removes neurons according to their significance. This provides further insight into the type of reservoir characteristics needed for a given task, and is supported by further reservoir measures of non-linearity and memory. These techniques are demonstrated on artificial and real world data.

show abstract

“…The subsequent use of a trainable non-recurrent linear readout layer combines the advantages of recurrent networks with the ease, efficiency and optimality of linear regression methods. New applications for processing temporal data have been reported, for instance in speech recognition [9,10], sensori-motor robot control [11][12][13], detection of diseases [14,15], or flexible central pattern generators in biological modeling [16].…”

Section: Introductionmentioning

confidence: 99%

Regularization by Intrinsic Plasticity and Its Synergies with Recurrence for Random Projection Methods

Neumann¹,

Emmerich²,

Steil³

2012

JILSA

View full text Add to dashboard Cite

Neural networks based on high-dimensional random feature generation have become popular under the notions extreme learning machine (ELM) and reservoir computing (RC). We provide an in-depth analysis of such networks with respect to feature selection, model complexity, and regularization. Starting from an ELM, we show how recurrent connections increase the effective complexity leading to reservoir networks. On the contrary, intrinsic plasticity (IP), a biologically inspired, unsupervised learning rule, acts as a task-specific feature regularizer, which tunes the effective model complexity. Combing both mechanisms in the framework of static reservoir computing, we achieve an excellent balance of feature complexity and regularization, which provides an impressive robustness to other model selection parameters like network size, initialization ranges, or the regularization parameter of the output learning. We demonstrate the advantages on several synthetic data as well as on benchmark tasks from the UCI repository providing practical insights how to use high-dimensional random networks for data processing

show abstract

P2.104 Gait analysis of autistic children with Echo State Networks

Cited by 5 publications

References 6 publications

Automatic Assessment of Motor Impairments in Autism Spectrum Disorders: A Systematic Review

Automatic Assessment of Motor Impairments in Autism Spectrum Disorders: A Systematic Review

Pruning reservoirs with Random Static Projections

Regularization by Intrinsic Plasticity and Its Synergies with Recurrence for Random Projection Methods

Contact Info

Product

Resources

About