Table 5 Baseline results for the chaotic function prediction task

From: The neurobench framework for benchmarking neuromorphic computing algorithms and systems

Baseline

sMAPE

Footprint (bytes)

Model Exec. Rate (Hz)

Connection Sparsity

Activation Sparsity

SynOps (per model exec.)

      

Dense

Eff_MACs

Eff_ACs

ESN

14.79

2.81 × 105

-

0.876

0.0

3.52 × 104

4.37 × 103

0

LSTM

13.37

4.90 × 105

-

0.0

0.530

6.03 × 104

6.03 × 104

0

  1. Execution rate is not reported as the data is a synthetic time series, with no real-time correlation.