学术文献库

This paper describes problems in AI research and how the SP System (described in an appendix) may help to solve them. Most of the problems are described by leading researchers in AI in interviews with science writer Martin Ford, and reported by him in his book {\em Architects of Intelligence}. These problems are: the need to bridge the divide between symbolic and non-symbolic kinds of knowledge and processing; the tendency of deep neural networks (DNNs) to make large and unexpected errors in recognition; the need to strengthen the representation and processing of natural languages; the challenges of unsupervised learning; the need for a coherent account of generalisation; how to learn usable knowledge from a single exposure; how to achieve transfer learning; how to increase the efficiency of AI processing; the need for transparency in AI structures and processes; how to achieve varieties of probabilistic reasoning; the need for more emphasis on top-down strategies; how to minimise the risk of accidents with self-driving vehicles; the need for strong compositionality in AI knowledge; the challenges of commonsense reasoning and commonsense knowledge; establishing the importance of information compression in AI research; establishing the importance of a biological perspective in AI research; establishing whether knowledge in the brain is represented in `distributed' or `localist' form; how to bypassing the limited scope for adaptation in deep neural networks; the need to develop `broad AI'; and how to eliminate the problem of catastrophic forgetting.