Table 1 Performance of a single layer feedforward neural network for raw events, histograms and HoG.

From: Photonic neuromorphic accelerators for event-based imaging flow cytometry

Metric

Max accuracy (%)

Mean accuracy (%)

Trainable parameters

FLOPS

Synthetic frames (100,100)

97.5

96.8 ± 0.7

30,003

60,001

Histogram (100)

90

88.6 ± 1.4

303

601

HoG (66,66)

98

97.5 ± 0.5

13,071

26,137

Back to article page