Neither deep neural networks nor symbolic AI alone has approached the kind of intelligence expressed in humans. This is mainly because neural networks are not able to decompose joint representations to obtain distinct objects (the so-called binding problem), while symbolic AI suffers from exhaustive rule searches, among other problems. These two problems are still pronounced in neuro-symbolic AI which aims to combine the best of the two paradigms. Here, we show that the two problems can be addressed with our proposed neuro-vector-symbolic architecture (NVSA) by exploiting its powerful operators on high-dimensional distributed representations that serve as a common language between neural networks and symbolic AI. The efficacy of NVSA is demonstrated by solving the Raven's progressive matrices datasets. Compared to state-of-the-art deep neural network and neuro-symbolic approaches, end-to-end training of NVSA achieves a new record of 87.7% average accuracy in RAVEN, and 88.1% in I-RAVEN datasets. Moreover, compared to the symbolic reasoning within the neuro-symbolic approaches, the probabilistic reasoning of NVSA with less expensive operations on the distributed representations is two orders of magnitude faster. Our code is available at https://github.com/IBM/neuro-vector-symbolic-architectures.

翻译：深度神经网络和符号人工智能均未能单独达到人类展现出的智能水平。这主要是因为神经网络无法分解联合表示以获得独立对象（即所谓的绑定问题），而符号人工智能则存在穷举规则搜索等问题。这两个问题在旨在结合两种范式优点的神经符号人工智能中依然突出。本文证明，通过利用所提出的神经-向量-符号架构（NVSA）在高维分布式表示上实现强大算子，可作为神经网络与符号人工智能之间的通用语言，从而解决上述两个问题。NVSA的有效性通过瑞文推理矩阵数据集得到验证。与最先进的深度神经网络和神经符号方法相比，NVSA的端到端训练在RAVEN数据集上实现了87.7%的平均准确率新纪录，在I-RAVEN数据集上达到88.1%。此外，相较于神经符号方法中的符号推理，NVSA通过分布式表示上计算代价更低的概率推理，速度提升了两个数量级。我们的代码可在https://github.com/IBM/neuro-vector-symbolic-architectures获取。