This paper describes how Tononi’s information integration theory of consciousness was used to make detailed predictions about the distribution of phenomenal states in a spiking neural network. This network had approximately 18,000 neurons and 700,000 connections and it used models of emotion and imagination to control the eye movements of a virtual robot and avoid ‘negative’ stimuli. The first stage in the analysis was the development of a formal definition of Tononi’s theory of consciousness. The network was then analysed for (...) information integration and detailed predictions were made about the distribution of consciousness for each time step of recorded activity. This work demonstrates how an artificial system can be analysed for consciousness using a particular theory and in the future this approach could be used to make predictions about the phenomenal states associated with biological systems. (shrink)

This paper is a review of the work that has been carried out on machine consciousness. A clear overview of this diverse field is achieved by breaking machine consciousness down into four different areas, which are used to understand its aims, discuss its relationship with other subjects and outline the work that has been carried out so far. The criticisms that have been made against machine consciousness are also covered, along with its potential benefits, and the work that has been (...) done on analysing systems for signs of consciousness. Some of the social and ethical issues raised by machine consciousness are examined at the end of the paper. (shrink)

As AI is linked to more and more aspects of our lives, the need for algorithms that can take decisions that are not only accurate but also fair becomes apparent. It can be seen both in discussions of future trends such as autonomous vehicles or the issue of superintelligence, as well as actual implementations of machine learning used to decide whether a person should be admitted in certain university or will be able to return a credit. In this paper, we (...) will use Dreyfus’ account on ethical expertise to show that, to give an AI some ability to make ethical judgements, a pure symbolic, conceptual approach is not enough. We also need the ability to make sense of the surroundings to reframe and define situations in a dynamic way, using multiple perspectives in a pre-reflective way. (shrink)

Standard, linguistic means of specifying the content of mental states do so by expressing the content in question. Such means fail when it comes to capturing non-conceptual aspects of visual experience, since no linguistic expression can adequately express such content. One alternative is to use depictions: images that either evoke (reproduce in the recipient) or refer to the content of the experience. Practical considerations concerning the generation and integration of such depictions argue in favour of a synthetic approach: the generation (...) of depictions through the use of an embodied, perceiving and acting agent, either virtual or real. This paper takes the first steps in an investigation as to how one might use a robot to specify the non-conceptual content of the visual experience of an (hypothetical) organism that the robot models. (shrink)