arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1811.00231q-bio.NCcs.LG
收藏

走向学会学习

Towards learning-to-learn

Department of Bioengineering, University of Pennsylvania(宾夕法尼亚大学生物工程系)

Benjamin James Lansdell, Konrad Paul Kording

摘要:

在老式的人工智能(GOFAI)中,人类指定了解决问题的系统。人工智能最近的大部分进展都来自于通过学习取代人类的洞察力。然而,学习本身通常仍然是由人类构建的--特别是参数更新应该遵循成本函数梯度的选择。然而,与GOFAI相比,没有理由相信人类特别擅长定义这样的学习系统:我们可能会期望学习本身更好,如果我们学习它,最近的机器学习研究已经开始意识到这种策略的好处。因此,我们应该期待这与神经科学相关:如何获得正确的学习规则?事实上,认知科学早就表明,人类学会了学习,这可能是他们令人印象深刻的学习能力的原因。在这里,我们讨论了跨机器学习、神经科学和认知科学的思想,这些思想对学习-学习的原则很重要。

英文摘要:

In good old-fashioned artificial intelligence (GOFAI), humans specified systems that solved problems. Much of the recent progress in AI has come from replacing human insights by learning. However, learning itself is still usually built by humans -- specifically the choice that parameter updates should follow the gradient of a cost function. Yet, in analogy with GOFAI, there is no reason to believe that humans are particularly good at defining such learning systems: we may expect learning itself to be better if we learn it. Recent research in machine learning has started to realize the benefits of that strategy. We should thus expect this to be relevant for neuroscience: how could the correct learning rules be acquired? Indeed, cognitive science has long shown that humans learn-to-learn, which is potentially responsible for their impressive learning abilities. Here we discuss ideas across machine learning, neuroscience, and cognitive science that matter for the principle of learning-to-learn.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑