We propose a retrieval-augmented convolutional network and propose to train it with local mixup, a novel variant of the recently proposed mixup algorithm. The proposed hybrid architecture combining a convolutional network and an off-theshelf retrieval engine was designed to mitigate the adverse effect of off-manifold adversarial examples, while the proposed local mixup addresses on-manifold one...

Article history: Received 2 April 2013 Received in revised form 25 July 2013 Accepted 26 July 2013 Available online xxxx Since the 1970s, automobile manufacturers have used electronics for safety–critical automobile control systems such as acceleration, braking, and steering. These electronic systems introduced functionalities in automobiles that were not feasible in a purely mechanical framewo...

We analyze alternative fuel-powertrain options for internal combustion engine automobiles. Fuel/engine efficiency, energy use, pollutant discharges, and greenhouse gas emissions are estimated for spark and compression ignited, direct injected (DI), and indirect injected (II) engines fueled by conventional and reformulated gasoline, reformulated diesel, compressed natural gas (CNG), and alcohols...

A model based control scheme is designed to regu late the cylinder air charge of a camless multicylinder engine for unthrottled operation The controller con sists of a feedforward and an adaptive feedback scheme based on a control oriented model of the breathing process of an engine equipped with electro hydraulic springless valve train The nonlinear control scheme is designed to achieve cylind...

This paper describes a cost-effective fuzzy control system applied to a small spark-ignition internal-combustion engine to achieve regulation of the fuel injection system. It determines the amount of fuel required from a fuzzy algorithm using engine speed and manifold air pressure as input values. The fuzzy control parameters were a collection of comprehensible rules and fuzzy-set membership fu...

This paper presents modelling of internal combustion (IC) engine with adaptive neural networks. A radial basis function network model with both centres and weights adapted and a model with only weights adapted are compared with a fixed parameter model. The developed models are used in model based predictive control (MPC) to form an adaptive nonlinear MPC scheme and applied to engine speed track...