Department of Bioengineering Sciences, Weihenstephan-Triesdorf University of Applied Sciences, Freising D-85354, Germany.
Computational Intelligence and Machine Learning Group, Department of Biophysics, University of Regensburg, Regensburg D-93053, Germany.
Comput Intell Neurosci. 2021 Nov 12;2021:5590445. doi: 10.1155/2021/5590445. eCollection 2021.
Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures. Humans seem to learn rich representations by exploration and imitation, build causal models of the world, and use both to flexibly solve new tasks. We suggest a simple but effective unsupervised model which develops such characteristics. The agent learns to represent the dynamical physical properties of its environment by intrinsically motivated exploration and performs inference on this representation to reach goals. For this, a set of self-organizing maps which represent state-action pairs is combined with a causal model for sequence prediction. The proposed system is evaluated in the environment. After an initial phase of playful exploration, the agent can execute kinematic simulations of the environment's future and use those for action planning. We demonstrate its performance on a set of several related, but different one-shot imitation tasks, which the agent flexibly solves in an active inference style.
人类的学习和智能与大多数深度学习架构所采用的监督模式识别方法不同。人类似乎通过探索和模仿来学习丰富的表示，建立对世界的因果模型，并利用这两者灵活地解决新任务。我们提出了一个简单但有效的无监督模型，该模型具有这些特点。该智能体通过内在激励的探索来学习表示环境的动态物理属性，并在此表示上进行推理以达到目标。为此，一组表示状态-动作对的自组织图与用于序列预测的因果模型相结合。所提出的系统在 环境中进行了评估。在初始的游戏探索阶段之后，智能体可以对环境未来的运动学进行模拟，并将其用于动作规划。我们在一组几个相关但不同的一次性模仿任务中展示了它的性能，智能体以主动推理的方式灵活地解决了这些任务。
