Search Results for author: Urmish Thakker

Found 13 papers, 4 papers with code

Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices

no code implementations14 Feb 2021 Urmish Thakker, Paul N. Whatmough, ZhiGang Liu, Matthew Mattina, Jesse Beu

Additionally, results with doped kronecker product matrices demonstrate state-of-the-art accuracy at large compression factors (10 - 25x) across 4 natural language processing applications with minor loss in accuracy.

Rank and run-time aware compression of NLP Applications

no code implementations EMNLP (sustainlp) 2020 Urmish Thakker, Jesse Beu, Dibakar Gope, Ganesh Dasika, Matthew Mattina

We evaluate the impact of this technique on 5 NLP benchmarks across multiple tasks (Translation, Intent Detection, Language Modeling) and show that for similar accuracy values and compression factors, HMF can achieve more than 2. 32x faster inference run-time than pruning and 16. 77% better accuracy than LMF.

Intent Detection Language Modelling +1

Benchmarking TinyML Systems: Challenges and Direction

1 code implementation10 Mar 2020 Colby R. Banbury, Vijay Janapa Reddi, Max Lam, William Fu, Amin Fazel, Jeremy Holleman, Xinyuan Huang, Robert Hurtado, David Kanter, Anton Lokhmotov, David Patterson, Danilo Pau, Jae-sun Seo, Jeff Sieracki, Urmish Thakker, Marian Verhelst, Poonam Yadav

In this position paper, we present the current landscape of TinyML and discuss the challenges and direction towards developing a fair and useful hardware benchmark for TinyML workloads.

Compressing Language Models using Doped Kronecker Products

no code implementations24 Jan 2020 Urmish Thakker, Paul N. Whatmough, Zhi-Gang Liu, Matthew Mattina, Jesse Beu

Kronecker Products (KP) have been used to compress IoT RNN Applications by 15-38x compression factors, achieving better results than traditional compression methods.

Language Modelling

Ternary MobileNets via Per-Layer Hybrid Filter Banks

no code implementations4 Nov 2019 Dibakar Gope, Jesse Beu, Urmish Thakker, Matthew Mattina

Using this proposed quantization method, we quantized a substantial portion of weight filters of MobileNets to ternary values resulting in 27. 98% savings in energy, and a 51. 07% reduction in the model size, while achieving comparable accuracy and no degradation in throughput on specialized hardware in comparison to the baseline full-precision MobileNets.

Quantization

Pushing the limits of RNN Compression

no code implementations4 Oct 2019 Urmish Thakker, Igor Fedorov, Jesse Beu, Dibakar Gope, Chu Zhou, Ganesh Dasika, Matthew Mattina

This paper introduces a method to compress RNNs for resource constrained environments using Kronecker product (KP).

A Static Analysis-based Cross-Architecture Performance Prediction Using Machine Learning

no code implementations18 Jun 2019 Newsha Ardalani, Urmish Thakker, Aws Albarghouthi, Karu Sankaralingam

Porting code from CPU to GPU is costly and time-consuming; Unless much time is invested in development and optimization, it is not obvious, a priori, how much speed-up is achievable or how much room is left for improvement.

Run-Time Efficient RNN Compression for Inference on Edge Devices

no code implementations12 Jun 2019 Urmish Thakker, Jesse Beu, Dibakar Gope, Ganesh Dasika, Matthew Mattina

Recurrent neural networks can be large and compute-intensive, yet many applications that benefit from RNNs run on small devices with very limited compute and storage capabilities while still having run-time constraints.

Edge-computing

Compressing RNNs for IoT devices by 15-38x using Kronecker Products

no code implementations7 Jun 2019 Urmish Thakker, Jesse Beu, Dibakar Gope, Chu Zhou, Igor Fedorov, Ganesh Dasika, Matthew Mattina

Recurrent Neural Networks (RNN) can be difficult to deploy on resource constrained devices due to their size. As a result, there is a need for compression techniques that can significantly compress RNNs without negatively impacting task accuracy.

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