arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.00076cs.LGcs.AIcs.RO
收藏

一种用于序列生成与识别的随机表示学习新框架

A Novel Framework for Learning Stochastic Representations for Sequence Generation and Recognition

Okinawa Institute of Science and Technology (OIST)(冲绳科学技术大学院大学);Samsung Research(三星研究中心);Geobotica(吉奥博蒂卡)

Jungsik Hwang, Ahmadreza Ahmadi

AI总结:

本文提出带参数偏置的随机循环神经网络(RNNPB),通过重参数化技巧在潜在空间引入随机性以学习序列的概率表示,实验表明其在运动序列生成与识别上优于确定性模型,并增强了不确定度量化和泛化能力。

摘要:

生成和识别序列数据的能力对于在动态环境中运行的自主系统至关重要。受大脑预测编码和贝叶斯大脑等关键原理的启发,我们提出了一种新颖的带参数偏置的随机循环神经网络(RNNPB)。该模型利用变分自编码器中使用的重参数化技巧,将随机性引入潜在空间。这种方法使模型能够学习多维序列的概率表示,捕捉不确定性并增强对过拟合的鲁棒性。我们在机器人运动数据集上测试了所提出的模型,以评估其在生成和识别时间模式方面的性能。实验结果表明,随机RNNPB模型在生成和识别运动序列方面优于其确定性对应模型。结果突出了所提出模型在学习和推理过程中量化和调整不确定性的能力。随机性带来了连续的潜在空间表示,有助于稳定的运动生成,并在识别新序列时增强泛化能力。我们的方法为时间模式建模提供了一个受生物学启发的框架,并推动了人工智能和机器人领域中鲁棒且自适应系统的发展。

英文摘要:

The ability to generate and recognize sequential data is fundamental for autonomous systems operating in dynamic environments. Inspired by the key principles of the brain-predictive coding and the Bayesian brain-we propose a novel stochastic Recurrent Neural Network with Parametric Biases (RNNPB). The proposed model incorporates stochasticity into the latent space using the reparameterization trick used in variational autoencoders. This approach enables the model to learn probabilistic representations of multidimensional sequences, capturing uncertainty and enhancing robustness against overfitting. We tested the proposed model on a robotic motion dataset to assess its performance in generating and recognizing temporal patterns. The experimental results showed that the stochastic RNNPB model outperformed its deterministic counterpart in generating and recognizing motion sequences. The results highlighted the proposed model's capability to quantify and adjust uncertainty during both learning and inference. The stochasticity resulted in a continuous latent space representation, facilitating stable motion generation and enhanced generalization when recognizing novel sequences. Our approach provides a biologically inspired framework for modeling temporal patterns and advances the development of robust and adaptable systems in artificial intelligence and robotics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑