To learn from one's mistakes: The role of impulsivity in positive workplace behaviours

Recentiy a neuropsychological model of learning has been proposed Qackson, 2002) which argues that Responsibility provides a cognitive re-expression of Impulsivit)' in the prediction of functional and dysfunctional behaviour. Jackson argues that primitive, instinctive impulses lead to antisocial behaviours and socio-cognitive regulators such as Responsibility leads to the re-expression of Impulsivity in terms of pro-social behaviours. Study 1 tests and supports the measurement properties of the assessment methodology associated with the model. Study 2 provides evidence in favour of the instinctive basis of Impulsivity and the conscious basis of Responsibility, which reinforces the underlying neuropsychological basis of the model. Study 3 uses structural equation modelling to determine if Responsibility mediates Impulsivity in the prediction of a latent variable representing work performance, work commitment and team performance, but does not mediate Impulsivit}' in the prediction of a latent variable representing sexual proclivity, workplace deviancy, gambling and beer consumption. Results provide strong support for Jackson's model and suggest that Impulsivity and Responsibility are fundamental to both functional and dysfunctional learning

Representation and learning of visual information for pose recognition

Recovering position from sensor information is an important problem in mobile robotics, known as localisation. Localisation requires a map or some other description of the environment to provide the robot with a context to interpret sensor data. The mobile robot system under discussion is using an artificial neural representation of position. Building a geometrical map of the environment with a single camera and artificial neural networks is difficult. Instead it would be simpler to learn position as a function of the visual input. Usually when learning images, an intermediate representation is employed. An appropriate starting point for biologically plausible image representation is the complex cells of the visual cortex, which have invariance properties that appear useful for localisation. The effectiveness for localisation of two different complex cell models are evaluated. Finally the ability of a simple neural network with single shot learning to recognise these representations and localise a robot is examined.