Yong Kiam Tan

Learn More
When doing an interactive proof about a piece of software, it is important that the underlying programming language's semantics does not make the proof unnecessarily difficult or unwieldy. Both small-step and big-step semantics are commonly used, and the latter is typically given by an inductively defined relation. In this paper, we consider an alternative:(More)
We have developed and mechanically verified a new compiler backend for CakeML. Our new compiler features a sequence of intermediate languages that allows it to incrementally compile away high-level features and enables verification at the right levels of semantic detail. In this way, it resembles mainstream (unverified) compilers for strict functional(More)
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(More)
To study the performance of sheet pile wall in peat during roadway construction, a long-term instrumentation program was conducted over a period of two years, measuring total lateral earth pressures, sheet pile deflections, soil movements, and water table level variances during construction. The analysis of field data indicated: ͑1͒ The earth pressure(More)
As part of a highway relocation project (RT44) in Carver Massachusetts, long sheet pile walls were installed in Cranbury bogs and ponds in order to mitigate environmental concerns. The subsurface consisting of deep peat deposits challenges the current understanding of the pressures developing on sheet piles and the parameters used for its design. A large(More)
This paper describes how the latest CakeML compiler supports verified compilation down to multiple realistically modelled target architectures. In particular, we describe how the compiler definition, the various language semantics, and the correctness proofs were organised to minimize target-specific overhead. With our setup we have incorporated compilation(More)
Deep Neural Networks (DNN) have been successful in enhancing 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(More)
  • 1