• Global robustness evaluation of deep neural networks with provable guarantees for the hamming distance 

  Ruan, W; Wu, M; Sun, Y; et al. (IJCAI, 16 August 2019)

  Deployment of deep neural networks (DNNs) in safety-critical systems requires provable guarantees for their correct behaviours. We compute the maximal radius of a safe norm ball around a given input, within which there are ...

• Concolic testing for deep neural networks 

  Sun, Y; Wu, M; Ruan, W; et al. (Association for Computing Machinery (ACM), 3 September 2018)

  Concolic testing combines program execution and symbolic analysis to explore the execution paths of a software program. This paper presents the first concolic testing approach for Deep Neural Networks (DNNs). More specifically, ...

• Reachability analysis of deep neural networks with provable guarantees 

  Ruan, W; Huang, X; Kwiatkowska, M (IJCAI, 19 July 2018)

  Verifying correctness of deep neural networks (DNNs) is challenging. We study a generic reachability problem for feed-forward DNNs which, for a given set of inputs to the network and a Lipschitz-continuous function over ...

• Gaussian process power curve models incorporating wind turbine operational variables 

  Pandit, RK; Infield, D; Kolios, A (Elsevier, 26 June 2020)

  The IEC standard 61400−12−1 recommends a reliable and repeatable methodology called ‘binning’ for accurate computation of wind turbine power curves that recognise only the mean wind speed at hub height and the air density ...

• Shape optimisation of the sharp-heeled Kaplan draft tube: Performance evaluation using Computational Fluid Dynamics 

  Daniels, SJ; Rahat, AAM; Tabor, GR; et al. (Elsevier / World Renewable Energy Network (WREN), 29 June 2020)

  A methodology to assess the performance of an elbow-type draft tube is outlined. This was achieved using Computational Fluid Dynamics (CFD) to evaluate the pressure recovery and mechanical energy losses along a draft tube ...

View more