Shape- and peak-sensitive goodness functions for Forward-Forward deliver up to 72pp gains over sum-of-squares, reaching 98.2% on MNIST and 89% on Fashion-MNIST.
EMNIST: E xtending MNIST to handwritten letters
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
New MDW benchmarks demonstrate that isolated digit classifiers struggle with multi-digit numbers from the same writer, necessitating task-specific metrics and advanced methods.
citing papers explorer
-
Selectivity and Shape in the Design of Forward-Forward Goodness Functions
Shape- and peak-sensitive goodness functions for Forward-Forward deliver up to 72pp gains over sum-of-squares, reaching 98.2% on MNIST and 89% on Fashion-MNIST.
-
Realistic Handwritten Multi-Digit Writer (MDW) Number Recognition Challenges
New MDW benchmarks demonstrate that isolated digit classifiers struggle with multi-digit numbers from the same writer, necessitating task-specific metrics and advanced methods.