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.

Investigating EFL teacher beliefs about teaching and learning

This article reports on research into the beliefs of a group of teachers working in the field of TESOL, specifically teachers of English as a Foreign Language (EFL). In particular, the aim was to see if it is possible to identify a coherent system of beliefs about teaching and learning that may account for different approaches to teaching.

Creativity and learning through electronic group causal mapping

This paper proposes, and begins to evaluate, a format of brainstorming-type activity which aims to release the creativity of participants and encourage them to learn about a wider range of issues in more detail. The format does this through providing a two-stage brainstorming session. After the first brainstorm, participants have an opportunity to both piggy-back off other peoples ideas (i.e. create new ideas by synthesising other peoples' ideas into their own perspectives), and share causal links to build a causal map with the brainstormed ideas. Five causal mapping sessions with organisations have been analysed. Findings suggest that ideas shared when piggy-backing are often highly creative and unique for the participant who shared them. Also piggy-backing and causal linking seem to provide effective opportunities for individual learning as participants have time to reflect upon other peoples' perspectives and share their own views on those.