The ability to sequentially learn from few examples and re-utilize previous knowledge is an important milestone on the path to artificial general intelligence. In this paper, we propose Teach Machine to Learn (TML), a few-shot learning model for hand-drawn multi-symbol sketch recognition. The model decomposes multi-symbol sketch into stroke primitives and then explains the observed sequences in a bayesian criterion. A Bidirectional Long Short Term Memory (BiLSTM) encoder is employed for stroke primitives encoding. Meanwhile, a probabilistic Hidden Markov Model (HMM) is constructed for complete sketch inference and recognition. The challenging task of hand-drawn multi-symbol sketch recognition is implemented on two public datasets. The comparative results indicate that the proposed method outperforms the currently booming image-based deep models in recognition accuracy. Furthermore, our method is capable to continuously learn new concepts even in one-shot. The codes are currently available in https://github.com/chongyupan/Teach-Machine-to-Learn.

能够从几个示例中顺序学习并重新利用先前的知识的能力，是通往人工智能的重要里程碑。在本文中，我们提出了“学习机器学习”（TML），这是用于手绘多符号草图识别的几次学习模型。该模型将多符号草图分解为笔划图元，然后以贝叶斯准则解释观察到的序列。双向长短期记忆（BiLSTM）编码器用于笔画图元编码。同时，建立了概率隐马尔可夫模型（HMM）以进行完整的草图推断和识别。手绘的多符号草图识别具有挑战性的任务是在两个公共数据集上实现的。对比结果表明，该方法在识别精度上优于目前正在兴起的基于图像的深度模型。此外，我们的方法即使一次也能不断学习新概念。这些代码目前可在https://github.com/chongyupan/Teach-Machine-to-Learn中获得。