About Me

Currently, I am a Code Reviewer @ Udacity. I work on building Machine Learning Models to support various Business Objectives and Decisions. Further, I am also involved in contributing to open source projects for different communities. My interest lies in Machine Learning, Data Science, Android Development and Full Stack Web Development.

Contact Details

Aditya Harsh
UPES
Dehradun, UK 248007 IN
(+91)885-927-4271
adityasiwan@live.com

Download Resume

Education

Udacity

Machine Learning Engineer Nanodegree• 2016

Gathered, cleaned, and processed large data sets to prepare them for analysis. Developed multiple models to describe the data in those sets, validate those models, and compared those models according to standard metrics. Converted the data model into a live system that can process and reach conclusions on real data. Optimized the system based on real-world constraints, such as desired accuracy, efficiency, resource availability, and real-time responsiveness. Deployed the system in a live environment, such as an autonomous car, or a recommender system.

University of Petroleum and Energy Studies

Bachelor of Computer Science• 2014-18

I am currently majoring in computer science at the University of Petroleum and Energy Studies, Dehradun.

Projects

TRAIN A SMART CAB TO DRIVE|MACHINE LEARNING

Python • July 2016

Using pygame, developed a reinforcement learning agent for a smart cab that needs to drop off its passenger to the goal state in the shortest time possible. Came up with two possible agents one being a naive random walk agent and the other implementing the q-leanrning strategy. Developed an algorithm to tweak when the agent needs to explore and when it needs to exploit using the q-learning policy it has developed based on the time left to drop off the passenger. The agent performed well in most of the trials it was subjected to. Currently it is being tweaked to learn a definite policy by training it for almost 100 trials.

CUSTOMER SEGMENTS|MACHINE LEARNING

Python • June 2016

Reviewed unstructured data to understand the patterns and natural categories that the data fits into. Used multiple algorithms and both empirically and theoretically compared and contrasted their results. Made predictions about the natural categories of multiple types in a dataset, then checked these predictions against the result of unsupervised analysis.

Skills

I'm very passionate about Machine Intelligence. Right now I'm focused on building Machine Learning Models to support various Business Objectives and Decisions.

  • C++
  • C
  • PYTHON
  • JAVA
  • HTML5
  • CSS

Client Testimonials

  • Whether it's the best of times or the worst of times, it's the only time we've got.

    Art Buchwald

  • I never had a policy; I have just tried to do my very best each and every day.

    Abraham Lincoln

  • To give anything less than your best, is to sacrifice the gift.

    Steve Prefontaine

Get In Touch.

Drop me a message and I'll get back to you soon :)

Error boy
Your message was sent, thank you!