no code implementations • 3 Oct 2023 • Ritesh Kumar, Saurabh Goyal, Ashish Verma, Vatche Isahagian
\\ We present \textbf{ProtoNER}: Prototypical Network based end-to-end KVP extraction model that allows addition of new classes to an existing model while requiring minimal number of newly annotated training samples.
1 code implementation • ICML 2020 • Saurabh Goyal, Anamitra R. Choudhury, Saurabh M. Raje, Venkatesan T. Chakaravarthy, Yogish Sabharwal, Ashish Verma
We demonstrate that our method attains up to 6. 8x reduction in inference time with <1% loss in accuracy when applied over ALBERT, a highly compressed version of BERT.
no code implementations • 20 Oct 2018 • Saurabh Goyal, Anamitra R Choudhury, Vivek Sharma, Yogish Sabharwal, Ashish Verma
Large number of weights in deep neural networks make the models difficult to be deployed in low memory environments such as, mobile phones, IOT edge devices as well as "inferencing as a service" environments on the cloud.
no code implementations • 1 Nov 2017 • Dharma Teja Vooturi, Saurabh Goyal, Anamitra R. Choudhury, Yogish Sabharwal, Ashish Verma
Large number of weights in deep neural networks makes the models difficult to be deployed in low memory environments such as, mobile phones, IOT edge devices as well as "inferencing as a service" environments on cloud.
1 code implementation • ICML 2017 • Ashish Kumar, Saurabh Goyal, Manik Varma
This paper develops a novel tree-based algorithm, called Bonsai, for efficient prediction on IoT devices – such as those based on the Arduino Uno board having an 8 bit ATmega328P microcontroller operating at 16 MHz with no native floating point support, 2 KB RAM and 32 KB read-only flash.
1 code implementation • ICML 2017 • Chirag Gupta, Arun Sai Suggala, Ankit Goyal, Harsha Vardhan Simhadri, Bhargavi Paranjape, Ashish Kumar, Saurabh Goyal, Raghavendra Udupa, Manik Varma, Prateek Jain
Such applications demand prediction models with small storage and computational complexity that do not compromise significantly on accuracy.