Tergel Molom-Ochir

Tergel Molom-Ochir

Undergraduate student, Electrical and Computer Engineering, University of Massachusetts Amherst

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

portfolio

publications

Design Considerations for Energy-efficient Inference on Edge Devices

Published in The 2nd International Workshop on Energy-Efficient Learning at the Edge, 1900

Abstract

The emergence oflow-power accelerators has enabled deep learning models to be executed on mobile or embedded edge devices without relying on cloud resources. The energy-constrained nature of these devices requires a judicious choice of a deep learning model and system configuration parameter to meet application needs while optimizing energy used during deep learning inference. In this paper, we carry out an experimental evaluation of more than 40 popular pretrained deep learning models to characterize trends in their accuracy, latency, and energy when running on edge accelerators. Our results show that as models have grown in size, the marginal increase in their accuracy has come at a much higher energy cost. Consequently, simply choosing the most accu- rate model for an application task comes at a higher energy cost; the application designer needs to consider the tradeoff between latency, accuracy, and energy use to make an appropriate choice. Since the relation between these metrics is non-linear, we present a recommendation algorithm to enable application designers to choose the best deep learning model for an application that meets energy budget constraints. Our results show that our technique can provide recommendations that are within 3 to 7% of the specified budget while maximizing accuracy and minimizing energy. CCS

MARCo: Solar Powered Autonomous Robotic Unmanned Surface Vehicle

Published in , 1900

Abstract

Autonomous sailboats have demonstrated that a robot could potentially perform long-term ocean monitoring and traveling. However, self-operating sailboats in the past had sails, which could lead to issues caused by tipping and heeling too much, and were not fully solar powered, which leads to short power endurance issues. Energy efficient and low cost autonomous robotic unmanned surface vehicle, named MARCo (Marine Autonomous Robotic Communicator), was programmed, developed and tested throughout the year 2018 in a public, co- educational university in Morehead, Kentucky. An off- grid solar system, which is comprised of 3x 20-Watt 12- Volt panels and a 12-Volt charge controller, was designed, constructed and installed on a 6ft surfboard to make it solar powered and to increase power- endurance with the help of power management algorithm written in Python. The boat is based on Raspberry Pi, a set of navigation sensors, and a ROCKBlock Iridium Modem. The project has been successful in building a solar-powered sailless autonomous unmanned surface vehicle. The boat was tested in diverse marine environments (Eagle Lake, KY and an indoor pool) and the results showing the overall performance of our boat, durability, energy consumption is presented.

Energy and Cost Considerations for GPU Accelerated AI Inference Workloads

Published in 2021 IEEE MIT Undergraduate Research Technology Conference (URTC), 1900

Abstract

Recent advances in AI have motivated hardware manufacturers to design deep learning friendly accelerators to keep with the ever-growing increases in model sizes and compu-tational requirements. While early accelerators were utilized for model training, newer accelerators are capable of running deep neural network (DNN) model inferences and are increasingly used in robotics, vision, and edge applications. In this paper, we compare several popular embedded and desktop GPUs with respect to their performance and energy efficiency. Our results show that although larger devices always provide higher throughput, they are not always the most energy-efficient. GPUs vary in terms of their energy efficiency. To aid the process of hardware selection for a system designer, we use our experimental results to design a recommendation algorithm that chooses the ideal hardware accelerator under cost, power, and performance constraints.

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.