Search Results for author: Keshab K. Parhi

Found 9 papers, 0 papers with code

SpikePipe: Accelerated Training of Spiking Neural Networks via Inter-Layer Pipelining and Multiprocessor Scheduling

no code implementations11 Jun 2024 Sai Sanjeet, Bibhu Datta Sahoo, Keshab K. Parhi

The mapping of various training tasks of the SNN onto systolic arrays is formulated, and the proposed scheduling method is evaluated on the three networks.


Robust Clustering using Hyperdimensional Computing

no code implementations5 Dec 2023 Lulu Ge, Keshab K. Parhi

To overcome this bottleneck, we assign the initial cluster hypervectors by exploring the similarity of the encoded data, referred to as \textit{query} hypervectors.


Tensor Decomposition for Model Reduction in Neural Networks: A Review

no code implementations26 Apr 2023 Xingyi Liu, Keshab K. Parhi

Modern neural networks have revolutionized the fields of computer vision (CV) and Natural Language Processing (NLP).

Image Classification Image Generation +2

Multi-Channel FFT Architectures Designed via Folding and Interleaving

no code implementations19 Feb 2022 Nanda K. Unnikrishnan, Keshab K. Parhi

Computing the FFT of a single channel is well understood in the literature.

LayerPipe: Accelerating Deep Neural Network Training by Intra-Layer and Inter-Layer Gradient Pipelining and Multiprocessor Scheduling

no code implementations14 Aug 2021 Nanda K. Unnikrishnan, Keshab K. Parhi

The proposed system, referred to as LayerPipe, reduces the number of clock cycles required for training while maximizing processor utilization with minimal inter-processor communication overhead.


Teaching Digital Signal Processing by Partial Flipping, Active Learning and Visualization

no code implementations31 Jan 2021 Keshab K. Parhi

Effectiveness of teaching digital signal processing can be enhanced by reducing lecture time devoted to theory, and increasing emphasis on applications, programming aspects, visualization and intuitive understanding.

Active Learning

PERMDNN: Efficient Compressed DNN Architecture with Permuted Diagonal Matrices

no code implementations23 Apr 2020 Chunhua Deng, Siyu Liao, Yi Xie, Keshab K. Parhi, Xuehai Qian, Bo Yuan

On the other hand, the recent structured matrix-based approach (i. e., CirCNN) is limited by the relatively complex arithmetic computation (i. e., FFT), less flexible compression ratio, and its inability to fully utilize input sparsity.

Model Compression

Classification using Hyperdimensional Computing: A Review

no code implementations19 Apr 2020 Lulu Ge, Keshab K. Parhi

Additionally, due to the nature of those three operations, HD computing leads to fast learning ability, high energy efficiency and acceptable accuracy in learning and classification tasks.

Binarization Classification +1

Automated OCT Segmentation for Images with DME

no code implementations24 Oct 2016 Sohini Roychowdhury, Dara D. Koozekanani, Michael Reinsbach, Keshab K. Parhi

For estimating the sub-retinal layer thicknesses, the proposed system has an average error of 0. 2-2. 5 $\mu m$ and 1. 8-18 $\mu m$ in normal and abnormal images, respectively.


Cannot find the paper you are looking for? You can Submit a new open access paper.