N
Naresh R. Shanbhag
Researcher at University of Illinois at Urbana–Champaign
Publications - 335
Citations - 10118
Naresh R. Shanbhag is an academic researcher from University of Illinois at Urbana–Champaign. The author has contributed to research in topics: Adaptive filter & CMOS. The author has an hindex of 49, co-authored 325 publications receiving 9202 citations. Previous affiliations of Naresh R. Shanbhag include Bell Labs & Wright State University.
Papers
More filters
Journal ArticleDOI
A pipelined adaptive NEXT canceller
Gi-Hong Im,Naresh R. Shanbhag +1 more
TL;DR: It is shown that this architecture can be clocked at a rate that is 107 times faster than the serial architecture with a maximum loss of 2.0 dB in signal-to-noise ratio (SNR).
Proceedings ArticleDOI
Instruction scheduling for low power on dynamically variable voltage processors
TL;DR: This paper proposes a timing-constrained and a resource- Constrained instruction scheduling algorithm for low power on pipelined functional units considering instruction latencies and pipelining effects.
Proceedings ArticleDOI
Statistical analysis of algorithmic noise tolerance
Eric P. Kim,Naresh R. Shanbhag +1 more
TL;DR: This paper proves a long held hypothesis that ANT has a strong Bayesian foundation, and develops an analytical framework for predicting the performance of, and designing performance-optimal ANT-based systems.
Proceedings ArticleDOI
Probabilistic Error Models for machine learning kernels implemented on stochastic nanoscale fabrics
Sai Zhang,Naresh R. Shanbhag +1 more
TL;DR: Performance prediction of the SVM using these models indicate that when compared with Monte Carlo with HDL generated error statistics, probability of detection pdet estimated using GEM-j is within 3% for VOS error when the error rate pη ≤ 80%, and within 5% for process variation error when supply voltage Vdd is between 0.3V and 0.7V.
Proceedings ArticleDOI
Low-power distributed arithmetic architectures using nonuniform memory partitioning
TL;DR: A rule governing the probability distribution of addresses to the memory is presented and it is used to partition the memory such that the most frequently accessed locations are stored in the smallest memory.