The best way to develop a Turing test passing AI is to follow the human model: an embodied agent that functions over a wide range of domains, is a human cognitive model, follows human neural functioning and learns. These properties will endow the agent with the deep semantics required to pass the test. An embodied agent functioning over a wide range of domains is needed to be exposed to and learn the semantics of those domains. Following human cognitive and neural functioning simplifies the search for sufficiently sophisticated mechanisms by reusing mechanisms that are already known to be sufficient. This is a difficult task, but initial steps have been taken, including the development of CABots, neural agents embodied in virtual environments. Several different CABots run in response to natural language commands, performing a cognitive mapping task. These initial agents are quite some distance from passing the test, and to develop an agent that passes will require broad collaboration. Several next steps are proposed, and these could be integrated using, for instance, the Platforms from the Human Brain Project as a foundation for this collaboration.
A previous attempt to categorize yeast proteins based on certain attributes yielded only a 55% success rate of correct categorisation using a new type of decision procedure [4]. This paper considers using existing soft computing approaches to improve the categorisation. More specijically, learning algorithms based on neural networks, growing cell systems, a rule development algorithm and genetic algorithms are applied to the yeast data. All of the results are at least as good as the original datu showing that new problems do not necessarily require new algorithms. More interestingly, as a consequence of using diferent algorithms, a consistent failure to achieve high success rates actually indicates features of the data rather than the failings of one or other of the algorithms.
A system with some degree of biological plausibility is developed to categorise items from a widely used machine learning benchmark. The system uses fatiguing leaky integrate and fire neurons, a relatively coarse point model that roughly duplicates biological spiking properties; this allows spontaneous firing based on hypo-fatigue so that neurons not directly stimulated by the environment may be included in the circuit. A novel compensatory Hebbian learning algorithm is used that considers the total synaptic weight coming into a neuron. The network is unsupervised and entirely self-organising. This is relatively effective as a machine learning algorithm, categorising with just neurons, and the performance is comparable with a Kohonen map. However the learning algorithm is not stable, and behaviour decays as length of training increases. Variables including learning rate, inhibition and topology are explored leading to stable systems driven by the environment. The model is thus a reasonable next step toward a full neural memory model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.