arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2011.11063cs.LGcs.PLstat.ML
收藏

像程序一样学习深度生成模型:自由类别先验

Learning a Deep Generative Model like a Program: the Free Category Prior

Eli Sennesh

摘要:

人类超越了大多数其他动物的认知能力,我们有能力将概念“组合”成单词,然后将单词组合成概念。在这个过程中,我们“无限利用有限的手段”,使我们能够快速学习新概念,并将概念嵌套在彼此之间。虽然程序归纳和综合仍然是人工智能基础理论的核心,但直到最近,社区才开始尝试将程序学习本身作为基准任务。因此,认知科学界经常假设,如果大脑具有与通用计算机相当的模拟和推理能力,那么它必须采用序列化的符号表示。在这里,我们面对这个假设,并提供一个反例,其中组合性通过网络结构来表达:优先于程序的自由类别。我们展示了我们的形式主义如何允许神经网络作为概率程序中的原语。我们端到端地学习程序结构和模型参数。

英文摘要:

Humans surpass the cognitive abilities of most other animals in our ability to "chunk" concepts into words, and then combine the words to combine the concepts. In this process, we make "infinite use of finite means", enabling us to learn new concepts quickly and nest concepts within each-other. While program induction and synthesis remain at the heart of foundational theories of artificial intelligence, only recently has the community moved forward in attempting to use program learning as a benchmark task itself. The cognitive science community has thus often assumed that if the brain has simulation and reasoning capabilities equivalent to a universal computer, then it must employ a serialized, symbolic representation. Here we confront that assumption, and provide a counterexample in which compositionality is expressed via network structure: the free category prior over programs. We show how our formalism allows neural networks to serve as primitives in probabilistic programs. We learn both program structure and model parameters end-to-end.

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。

↑