Biologically-plausible learning algorithms can scale to large datasets

The backpropagation (BP) algorithm is often thought to be biologically implausible in the brain. One of the main reasons is that BP requires symmetric weight matrices in the feedforward and feedback pathways... (read more)

PDF Abstract ICLR 2019 PDF ICLR 2019 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Biologically-plausible Training ImageNet ResNet-18, Feedback Alignment Top-1 Error Rate 90.52 # 2
Top 5 Error Rate 77.32 # 2
Biologically-plausible Training ImageNet ResNet-18, Sign-symmetry Top-1 Error Rate 37.91 # 1
Top 5 Error Rate 16.18 # 1

Methods used in the Paper