arXiv subjects

Yong Kiam Tan

Publications and source records attributed to Yong Kiam Tan.

22 records · Page 2Linked to original sources

arXiv2019

A Formal Safety Net for Waypoint Following in Ground Robots

We present a reusable formally verified safety net that provides end-to-end safety and liveness guarantees for 2D waypoint-following of Dubins-type ground robots with tolerances and acceleration. We: i) Model a robot in differential dynamic logic (dL), and specify assumptions on the controller and robot kinematics, ii) Prove formal safety and liveness properties for waypoint-following with speed limits, iii) Synthesize a monitor, which is automatically proven to enforce model compliance at runtime, and iv) Our use of the VeriPhy toolchain makes these guarantees carry over down to the level of machine code with untrusted controllers, environments, and plans. The guarantees for the safety net apply to any robot as long as the waypoints are chosen safely and the physical assumptions in its model hold. Experiments show these assumptions hold in practice, with an inherent trade-off between compliance and performance.

cs.RO↗

arXiv2019

Differential Equation Axiomatization: The Impressive Power of Differential Ghosts

We prove the completeness of an axiomatization for differential equation invariants. First, we show that the differential equation axioms in differential dynamic logic are complete for all algebraic invariants. Our proof exploits differential ghosts, which introduce additional variables that can be chosen to evolve freely along new differential equations. Cleverly chosen differential ghosts are the proof-theoretical counterpart of dark matter. They create new hypothetical state, whose relationship to the original state variables satisfies invariants that did not exist before. The reflection of these new invariants in the original system then enables its analysis. We then show that extending the axiomatization with existence and uniqueness axioms makes it complete for all local progress properties, and further extension with a real induction axiom makes it complete for all real arithmetic invariants. This yields a parsimonious axiomatization, which serves as the logical foundation for reasoning about invariants of differential equations. Moreover, our results are purely axiomatic, and so the axiomatization is suitable for sound implementation in foundational theorem provers.

cs.LO↗

arXiv2016

Improved Recurrent Neural Networks for Session-based Recommendations

Recurrent neural networks (RNNs) were recently proposed for the session-based recommendation task. The models showed promising improvements over traditional recommendation approaches. In this work, we further study RNN-based models for session-based recommendations. We propose the application of two techniques to improve model performance, namely, data augmentation, and a method to account for shifts in the input data distribution. We also empirically study the use of generalised distillation, and a novel alternative model that directly predicts item embeddings. Experiments on the RecSys Challenge 2015 dataset demonstrate relative improvements of 12.8% and 14.8% over previously reported results on the Recall@20 and Mean Reciprocal Rank@20 metrics respectively.

cs.LG↗

arXiv2016

Multi-Modal Hybrid Deep Neural Network for Speech Enhancement

Deep Neural Networks (DNN) have been successful in en- hancing noisy speech signals. Enhancement is achieved by learning a nonlinear mapping function from the features of the corrupted speech signal to that of the reference clean speech signal. The quality of predicted features can be improved by providing additional side channel information that is robust to noise, such as visual cues. In this paper we propose a novel deep learning model inspired by insights from human audio visual perception. In the proposed unified hybrid architecture, features from a Convolution Neural Network (CNN) that processes the visual cues and features from a fully connected DNN that processes the audio signal are integrated using a Bidirectional Long Short-Term Memory (BiLSTM) network. The parameters of the hybrid model are jointly learned using backpropagation. We compare the quality of enhanced speech from the hybrid models with those from traditional DNN and BiLSTM models.

cs.LG↗