ASTOUND

Even if state of the art AI can solve some problems as competently as a human, it may not have a broader context to judge the value of the solution, especially when handling new and unexpected situations. Humans leverage their awareness, but what about machines?

Given current technology, it should be possible to build a machine that contains a model of consciousness. That machine would attribute consciousness to itself and to the people it interacts with. Moreover, it would use that attribution to make predictions about human behaviour and to put input data in context. It is the Alien AI Lab’s objective to build a machine with such capabilities, through the Astound project.

The ASTOUND project will provide an Integrative Approach For Awareness Engineering to establish consciousness in machines. To achieve this goal the project will focus on the following activities:

• Develop an AI architecture for Artificial Consciousness based on the Attention Schema Theory (AST). It is a novel approach to human and social cognition that reconciles several cognitive neuroscience theories of consciousness, stating that subjective awareness results from the construction of an internal model of the “state of attention”.
• Implement the developed architecture into a contextually-aware conversational agent. This is to verify the hypothesis that an artificial consciousness based on AST will unambiguously improve selection of appropriate language registry, adaptation to the interlocutor, and long term coherence.

ASTOUND proposes to build a plausible human-brain architecture for consciousness capable of demonstrating an undeniable added value in terms of human-machine interaction. This will be obtained by combining state of the art deep neural networks models with an Attention Schema.

The Attention Schema Theory (AST) , first conceived by Dr. Michael Graziano (Princeton Neuroscience Institute, part of ASTOUND’s team), explains the brain basis of subjective awareness in a mechanistic and scientifically testable manner. According to the AST, the brain is an information-processing device with the capacity to focus its processing resources more on some signals than on others. The theory proposes that brains construct subjective awareness as a schematic model of the process of attention. Dr. Graziano’s team trained an artificial deep Q-learning neural network agent to control a simple form of visuospatial attention, tracking a stimulus with an attention spotlight to solve a catching task. The results show how the presence of even a simple attention schema can provide a profound benefit as a controller of attention. Dr. Graziano will collaborate now with Alien AI Lab to highlight the implications of the Attention Schema Theory on the generation and understanding of language, which are human specific abilities, which are related to consciousness in a more subtle, but maybe even deeper, way than visuospatial attention.