This work improves the efficiency of dynamic pruning algorithms by introducing a new posting iterator that can skip large parts of the matching documents during top-k query processing. Namely, the conditional-skip iterator jumps to a target document while skipping all matching documents preceding the target that cannot belong to the final result list. We experiment with two implementations of t...

Scheduling is considered the most important task in a high-level synthesis process. A heuristic algorithm based on the A search to find optimal schedules quickly is presented. This algorithm reduces the computational effort required to obtain the best schedules on a pre-defined datapath by effectively pruning the non-promising search space. The pruning method is accomplished by an admissible he...

In this article we describe HiFST, a lattice-based decoder for hierarchical phrase-based translation and alignment. The decoder is implemented with standard Weighted Finite-State Transducer (WFST) operations as an alternative to the well-known cube pruning procedure. We find that the use of WFSTs rather than k-best lists requires less pruning in translation search, resulting in fewer search err...

The paper presents a method for performance improvements of a speech recognition system by moving a part of the computation acoustic likelihood computation onto a Graphics Processor Unit (GPU). In the system, GPU operates as a low cost powerful coprocessor for linear algebra operations. The paper compares GPU implementation of two techniques of acoustic likelihood computation: full Gaussian com...

Winogradand FFT-based convolution are two efficient convolution algorithms targeting high-performance inference. Their efficiency comes from the reduction of the number of multiplication operations due to linear and Fourier transforms. However, the two existing approaches cannot handle efficient compression of the neural network, which might contribute significant improvement in computation and...

Abs t rac t . Artificial neural networks can solve complex problems such as time Series prediction, handwritten pattern recognition or speech processing. Though software simulations are essential when one sets about to study a new algorithm, they cannot always fulfill real-time criteria required by some practical applications. Consequently, hardware implementations are of crucial import. The ap...

Waste management is a current and transversal problem in all production areas, including agriculture. Within this economic activity, wine generates large amount of waste, namely, that resulting from the winemaking activity itself, such as pomace grape stalks, waste vineyards, with operations vine pruning. The pruning residuals has traditionally been conducted by burning leftovers on-site, witho...

Deep-learning-based applications bring impressive results to graph machine learning and are widely used in fields such as autonomous driving language translations. Nevertheless, the tremendous capacity of convolutional neural networks makes it difficult for them be implemented on resource-constrained devices. Channel pruning provides a promising solution compress by removing redundant calculati...

The high quality and quantity seed production in old saxual shrubs are essential for regeneration and sustainable development of saxual forests in desert areas. The objective of this study was to determine the effects of different pruning height on saxual seed production. The study was carried out in an obviously wilted saxual forest located in Ashkezar desert in Yazd in 1994. The experiment wa...

 Knowledge of the Saxaul dimensions used in sand dunes stabilization is considered essential for designing live windbreak in desert regions. This research aimed to collect and analysis data and was performed on the pruned and control shrubs of Haloxylon aphyllum L. in Yazd province, Iran in the last two decades. Our review clearly showed the superiority of shrubs pruned at the height of 35 cm i...