We develop artificial neural networks which extract structure from visual data. We explore an extension of Hebbian Learning which has been called ɛ- Insensitive Hebbian Learning and show that it may be thought of as a special case of Maximum Likelihood Hebbian learning and investigate the resulting network with both real and artificial data. We show that the resulting network is able to identify a single orientation of bars from a mixture of horizontal and vertical bars and also it is able to identify local filters from video images.