Recurrent Attentive Neural Process for Sequential Data
This work solves the issue of modeling sequential data with uncertainty for applications like robotics and autonomous driving, but it is incremental as it combines existing methods (ANP and RNN).
The paper tackled the problem of Neural Processes (NPs) being limited in capturing temporal order and recurrent structure from sequential data due to permutation invariance, and proposed Recurrent Attentive Neural Process (RANP) to address this. The result showed that RANP outperformed NPs and LSTMs in a 1D regression toy example and autonomous-driving applications.
Neural processes (NPs) learn stochastic processes and predict the distribution of target output adaptively conditioned on a context set of observed input-output pairs. Furthermore, Attentive Neural Process (ANP) improved the prediction accuracy of NPs by incorporating attention mechanism among contexts and targets. In a number of real-world applications such as robotics, finance, speech, and biology, it is critical to learn the temporal order and recurrent structure from sequential data. However, the capability of NPs capturing these properties is limited due to its permutation invariance instinct. In this paper, we proposed the Recurrent Attentive Neural Process (RANP), or alternatively, Attentive Neural Process-RecurrentNeural Network(ANP-RNN), in which the ANP is incorporated into a recurrent neural network. The proposed model encapsulates both the inductive biases of recurrent neural networks and also the strength of NPs for modelling uncertainty. We demonstrate that RANP can effectively model sequential data and outperforms NPs and LSTMs remarkably in a 1D regression toy example as well as autonomous-driving applications.