Led by a team from the Institute of Automation, Chinese Academy of Sciences, this study explores a new frontier in machine learning. With the rise of large language models, AI is evolving from perceptual intelligence to cognitive intelligence, and human language has become a pivotal component of visual understanding. This study questions whether machines can spontaneously learn a machine language as a visual representation, without relying on human language.
Inspired by the strengths of human language, the researchers began by simulating the emergence of language in the most basic scenario of a two-agent game. Their aim was to generate a language through the interactions of these agents. Using the 'Speak, Guess, and Draw' game as a platform, the researchers demonstrate the capabilities of neural networks in generating variable-length, discrete, and semantic representations.
The team also validated its potential advantage by comparing discrete language with continuous features from three perspectives: interpretability, generalization, and robustness across diverse datasets.
The study of machine language represents an exciting and valuable direction in artificial intelligence research. Imagine a future where AI development is no longer limited to fixed programs and predefined rules, but allows intelligent agents to freely evolve in a specific environment, communicating and collaborating through spontaneous language.
See the article:
Emergence of Machine Language: Towards Symbolic Intelligence with Neural Networks
https://doi.org/10.1093/nsr/nwad317
National Science Review