Attention-based sequence-to-sequence models for automatic speech recognition jointly train an acoustic model, language model, and alignment mechanism. Thus, the language model component is only trained on transcribed audio-text pairs. This leads to the use of shallow fusion with an external language model at inference time. Shallow fusion refers to log-linear interpolation with a separately tra...

Generalized Linear Models (GLMs) and Single Index Models (SIMs) provide powerful generalizations of linear regression, where the target variable is assumed to be a (possibly unknown) 1-dimensional function of a linear predictor. In general, these problems entail non-convex estimation procedures, and, in practice, iterative local search heuristics are often used. Kalai and Sastry (2009) recently...

Simultaneous production planning and scheduling has been identified as one of the most important factors that affect the efficient implementation of planning and scheduling operations for the production systems. In this paper, simultaneous production planning and scheduling is applied in a hybrid flow shop environment, which has numerous applications in real industrial settings. In this problem...

purpose:the user interface of federated search engines is very important because it can make effective search, retrieval, and user interaction with the system. . identifying the most important indicators of the federated search engine user interface is a solution to enhance the applicability of the search engine interface. the purpose of this study was to examine the role of search, screen, nav...

Toxicity of 38 aliphatic carboxylic acids was studied using non-linear quantitative structure-toxicityrelationship (QSTR) models. The adaptive neuro-fuzzy inference system (ANFIS) was used to construct thenonlinear QSTR models in all stages of study. Two ANFIS models were developed based upon differentsubsets of descriptors. The first one used log ow K and LUMO E as inputs and had good predicti...

This paper concerns prediction and calibration in generalized linear models. A new predictive procedure, giving improved prediction intervals, is briefly reviewed and further theoretical results, useful for calculations, are presented. Indeed , the calibration problem is faced within the classical approach and a suitable solution is obtained by inverting the associated improved prediction proce...