Representation is a core issue in artificial intelligence. Humans use discrete language to communicate and learn from each other, while machines use continuous features (like vector, matrix, or tensor in deep neural networks) to represent cognitive patterns. Discrete symbols are low-dimensional, decoupled, and have strong reasoning ability, while continuous features are high-dimensional, coupled, and have incredible abstracting capabilities. In recent years, deep learning has developed the idea of continuous representation to the extreme, using millions of parameters to achieve high accuracies. Although this is reasonable from the statistical perspective, it has other major problems like lacking interpretability, poor generalization, and is easy to be attacked. Since both paradigms have strengths and weaknesses, a better choice is to seek reconciliation. In this paper, we make an initial attempt towards this direction. Specifically, we propose to combine symbolism and connectionism principles by using neural networks to derive a discrete representation. This process is highly similar to human language, which is a natural combination of discrete symbols and neural systems, where the brain processes continuous signals and represents intelligence via discrete language. To mimic this functionality, we denote our approach as machine language. By designing an interactive environment and task, we demonstrated that machines could generate a spontaneous, flexible, and semantic language through cooperation. Moreover, through experiments we show that discrete language representation has several advantages compared with continuous feature representation, from the aspects of interpretability, generalization, and robustness.
翻译:人类使用离散的语言相互交流和学习,而机器则使用连续的特征(如矢量、矩阵或深神经网络中的超强)来代表认知模式。分辨符号是低维的,分解的,具有很强的推理能力,而连续特征是高维的,结合的,具有令人难以置信的抽象能力。近年来,深层次的学习发展了持续代表至极端的理念,使用数百万个参数实现高度理解性。尽管从统计角度讲,这是合理的,但它还有其他主要问题,如缺乏解释性、不全面化或深神经网络中的强弱等,很容易受到攻击。由于两种模式都有长处和弱点,因此更好的选择是寻求调和。在本文中,我们初步尝试了朝这个方向努力。具体地说,我们建议通过神经网络将符号和联系原则结合起来,以获得离散的表达。这一过程与人类语言的自然结合,这是离散符号和神经系统的自然组合,在这个系统中,大脑通过离散语言处理连续的信号和显示智能,并且很容易受到攻击。我们通过交互式的功能,我们通过一个互动的实验,我们通过一个自动的语言来展示了一种自发的语言的实验,我们通过一个自我解释,我们展示了一种自动的语言的方法展示了一种自动的特征的特征,我们展示了一种感变的特征的特征的特征,我们展示了一种环境的特征,我们通过一种感化的方法,我们展示了一种自动的实验,通过一种感变的特征,我们所展示了一种感化的方法,我们所展示了一种自动的特征。