Initial network setup

All 4 instances share the same initial W and Win matrices

Estimators setup

Transfer entropy

Active information storage

TE matrix

Measures

Significance test for differences in mean square error (MSE) using Wilcoxon signed-rank test

Reservoir TE distribution

AIS

Initial network setup

All 4 instances share the same initial W and Win matrices

Estimators setup

Transfer entropy

Active information storage

TE matrix

 

 

Measures

TE matrix

in 42 for Mackey – Glass scaled 0.9 setup there are two nodes. So I tried the second most frequent one.

Estimators setup

Significance test for differences in mean square error (MSE) using Wilcoxon signed-rank test

Differences in mean square error (MSE) of Scaled 0.5 – Scaled 0.9 – OG – ON  using Friedman test gives p-value=0.3172

Reservoir TE distribution

AIS

Initial network setup

All 4 instances share the same initial W and Win matrices

Estimators setup

Transfer entropy

Active information storage

TE matrix

 

Measures

Significance test for differences in mean square error (MSE) using Wilcoxon signed-rank test

Reservoir TE distribution

 

AIS

Initial network setup

All 4 instances share the same initial W and Win matrices

Estimators setup

Transfer entropy

Active information storage

TE matrix

 

Measures

Reservoir TE distribution

 

AIS

Initial network setup

Memory capacity task

Parameters with max counts

NARMA

Parameters with max counts

Mackey – Glass

Parameters with max counts

Lorenz

Parameters with max counts

Initial network setup

All 4 instances share the same initial W and Win matrices

Estimators setup

Transfer entropy

Active information storage

TE matrix

Significance test for differences in mean square error (MSE) using Wilcoxon signed-rank test

Reservoir TE distribution

 

AIS

 

Source files:

NARMATEsigNumba.py
NARMATEnormalizedSigNumba.py
NARMATEOGSigNumba_n.py
NARMATEONSigNumba_n.py

Initial network setup

All 4 instances share the same initial W and Win matrices

Estimators setup

Transfer entropy

Active information storage

TE matrix

Measures

Reservoir TE distribution

 

AIS

 

Source files:
TEMCsigNumba_n.py
TEMCnormalizedSigNumba_n.py
TEMCOGSigNumba_n.py
TEMCONSigNumba_n.py

Initial network setup

Estimators setup

 

 

Significance test for differences in mean square error (MSE) using Wilcoxon signed-rank test

Reservoir TE distribution

 

AIS

Source files:

NARMATEsigNumba.py
NARMATEnormalizedSigNumba.py
NARMATEOGSigNumba_n.py
NARMATEONSigNumba_n.py

Initial network setup

Estimators setup

 

Reservoir TE distribution

 

AIS

Source files:
TEMCsigNumba_n.py
TEMCnormalizedSigNumba_n.py
TEMCOGSigNumba_n.py
TEMCONSigNumba_n.py

Unscaled reservoir

Initial network setup

 

Scaled reservoir

Initial network setup

OG reservoir

Initial network setup

ON reservoir

Initial network setup

Source files:

embeddingLorenz_n.py
embeddingMC_n.py
embeddingMG_n.py
embeddingNARMA_n.py