Optimal Input Gain: All You Need to Supercharge a Feed-Forward Neural Network
Linear transformation of the inputs alters the training performance of feed-forward networks that are otherwise equivalent. However, most linear transforms are viewed as a pre-processing operation separate from the actual training. Starting from equivalent networks, it is shown that pre-processing i...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Linear transformation of the inputs alters the training performance of
feed-forward networks that are otherwise equivalent. However, most linear
transforms are viewed as a pre-processing operation separate from the actual
training. Starting from equivalent networks, it is shown that pre-processing
inputs using linear transformation are equivalent to multiplying the negative
gradient matrix with an autocorrelation matrix per training iteration. Second
order method is proposed to find the autocorrelation matrix that maximizes
learning in a given iteration. When the autocorrelation matrix is diagonal, the
method optimizes input gains. This optimal input gain (OIG) approach is used to
improve two first-order two-stage training algorithms, namely back-propagation
(BP) and hidden weight optimization (HWO), which alternately update the input
weights and solve linear equations for output weights. Results show that the
proposed OIG approach greatly enhances the performance of the first-order
algorithms, often allowing them to rival the popular Levenberg-Marquardt
approach with far less computation. It is shown that HWO is equivalent to BP
with Whitening transformation applied to the inputs. HWO effectively combines
Whitening transformation with learning. Thus, OIG improved HWO could be a
significant building block to more complex deep learning architectures. |
---|---|
DOI: | 10.48550/arxiv.2303.17732 |