Machine Learning-Based Pruning Technique for Low Power Approximate Computing  

作　　者：B.Sakthivel K.Jayaram N.Manikanda Devarajan S.Mahaboob Basha S.Rajapriya 

机构地区：[1]Department of Electronics and Communication Engineering,Madurai Institute of Engg and Technology,Sivagangai,Tamilnadu,630611,India [2]Pilecubes India Pvt Ltd.,Chennai,Tamilnadu,India [3]Department of Electronics and Communication Engineering,Malla Reddy Engineering College(Autonomous),Secunderabad,500100,India [4]Department of Electronics and Communication Engineering,R.M.K.Engineering College,Kavaraipettai,Chennai,Tamil Nadu,601206,India [5]Department of Electronics and Communication Engineering,K Ramakrishnan College of Engineering,Kariyamanickam Rd,Tamil Nadu,621112,India

出　　处：《Computer Systems Science & Engineering》2022年第7期397-406,共10页计算机系统科学与工程（英文）

摘　　要：Approximate Computing is a low power achieving technique that offers an additional degree of freedom to design digital circuits.Pruning is one of the types of approximate circuit design technique which removes logic gates or wires in the circuit to reduce power consumption with minimal insertion of error.In this work,a novel machine learning(ML)-based pruning technique is introduced to design digital circuits.The machine-learning algorithm of the random forest deci-sion tree is used to prune nodes selectively based on their input pattern.In addi-tion,an error compensation value is added to the original output to reduce an error rate.Experimental results proved the efficiency of the proposed technique in terms of area,power and error rate.Compared to conventional pruning,proposed ML pruning achieves 32%and 26%of the area and delay reductions in 8*8 multi-plier implementation.Low power image processing algorithms are essential in various applications like image compression and enhancement algorithms.For real-time evaluation,proposed ML optimized pruning is applied in discrete cosine transform(DCT).It is a basic element of image and video processing applications.Experimental results on benchmark images show that proposed pruning achieves a very good peak signal-to-noise ratio(PSNR)value with a considerable amount of energy savings compared to other methods.

关 键 词：Machine learning PRUNING approximate computing PSNR 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]