Publication View

Uniqueness of weights for neural networks (1993)

Abstract
In most applications dealing with learning and pattern recognition, neural nets are employed as models whose parameters, or “weights, ” must be fit to training data. Gradient descent and other algorithms are used in order to minimize an error functional, which penalizes mismatches between the

Publication details
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.2840
Source http://www.math.rutgers.edu/~sontag/FTP_DIR/92caip.pdf
Publisher Chapman and Hall
Contributors CiteSeerX
Repository CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Type text
Language English
Relation 10.1.1.29.6931, 10.1.1.48.3536, 10.1.1.55.7378, 10.1.1.51.3409, 10.1.1.44.5744, 10.1.1.50.8970, 10.1.1.49.8669, 10.1.1.52.1694, 10.1.1.49.6388, 10.1.1.38.920, 10.1.1.74.2969, 10.1.1.41.5460, 10.1.1.27.8586, 10.1.1.49.789, 10.1.1.57.1663, 10.1.1.49.1721, 10.1.1.52.2348, 10.1.1.53.7677, 10.1.1.104.5410, 10.1.1.36.4109, 10.1.1.41.4485, 10.1.1.62.6665, 10.1.1.51.5436