Browsing by Subject "Pruning"

Now showing 1 - 4 of 4

Open Access
A tree pruning technique for decoding complexity reduction of polar codes and PAC codes
(Institute of Electrical and Electronics Engineers , 2023-05-18) Moradi, Mohsen; Mozammel, Amir
Sorting operation is one of the main bottlenecks for the successive-cancellation list (SCL) decoding. This paper introduces an improvement to the SCL decoding for polar and pre-transformed polar codes that reduces the number of sorting operations without visible degradation in the code’s error correction performance. In an SCL decoding with an optimum metric function we show that, on average, the correct branch’s bit-metric value must be equal to the bit-channel capacity, and on the other hand, the average bit-metric value of a wrong branch can be at most zero. This implies that a wrong path’s partial path metric value deviates from the bit-channel capacity’s partial summation. For relatively reliable bit-channels, the bit metric for a wrong branch becomes very large negative number, which enables us to detect and prune such paths. We prove that, for a threshold lower than the bit-channel cutoff rate, the probability of pruning the correct path decreases exponentially by the given threshold. Based on these findings, we presented a pruning technique, and the experimental results demonstrate a substantial decrease in the amount of sorting procedures required for SCL decoding. In the stack algorithm, a similar technique is used to significantly reduce the average number of paths in the stack.
Open Access
A constraint-based incremental approach for update of large itemsets
(2001-08) Demir, Engin
Embargo
Efficient neural network processing via model compression and low-power functional units
(2024-12) Karakuloğlu, Ali Necat
We present a framework that contributes neural network optimization through novel methods in pruning, quantization, and arithmetic unit design for resource-constrained devices to datacenters. The first component is a pruning method that employs an importance metric to measure and selectively eliminate less critical neurons and weights, achieving high compression rates up to 99.9% without sacrificing significant accuracy. This idea is improved by a novel pruning schedule that optimizes the balance between compression and model’s generalization capa-bility. Next, we introduce a quantization method that combines with pruning to improve hardware compatibility for floating point format, offering efficient model compression and fast computation and general usability. Finally, we propose a logarithmic arithmetic unit that designed as an energy-efficient alternative to conventional floating-point operations, providing precise and configurable processing without relying on bulky lookup tables. Extensive evaluations across different datasets and CUDA-based simulations and Verilog based hardware designs indicate that our approaches outperforms existing methods, making it a powerful solution for deploying artificial intelligence models more efficiently.
Open Access
New Keynesian small open economy: Turkish case
(2016-06) Ersoy, Sedat
Turkey experienced substantial declines in inflation after 2002. Was it due to good policy, good luck, or both? To address this question, we incorporate stochastic volatility into a small open new Keynesian model of Monacelli (2005). As demonstrated by Fernandez-Villaverde, Guerron-Quintana, Rubio-Ramirez (2010), volatility shocks are an importance source of macroeconomic fluctuations so they need to be accounted for in order to examine the good luck hypothesis rigorously. Our estimated model suggests that both good policy and good luck played roles in bringing down the inflation.