Ashutosh Kumar Nirala

Aspiration: Contribution towards AGI.

Ashutosh Kumar Nirala email: aknirala@iastate.edu akn.nirala@gmail.com
Currently in third year of PhD (started in Fall'17) from Iowa State University, Computer Science Department. (Resume: 1pg, 2pg)

PhD Stuff (at ISU): Aug 2017 - current

Thesis Research: I am pursuing my PhD under Prof Jin Tian. My research revolves around learning Bayesian Networks from data. My thesis would be (as per current plan) to learn m-graph [Ref: K Mohan 2013] from missing data: i.e., given a data containing missing values, devise techniques to learn Bayesian Networks where variables causing missingness are also present.
Currently however I am trying to tackle a bit simpler problem, with no missing data, wherein I am working with different search spaces to learn Bayesian Network more efficiently. Specifically I am exploring if search in partition space [Ref: J. Kuipers and G. Moffa], could give better/faster results as compared to ordered space [Ref: Mare and D Koller 2005; Muro 2015]. Specifically, I am trying to adapt code present here, by mauro-idsia.
Research Assistant work: Working with Dr Adisak Sukul on NSF funded project. Project involves: automated collection and coding of online campaign advertising. It has four major steps:
1. Collecting YouTube ads from different US states with different age and sex profiles (currently on this step).
2. Classifying the political and nonpolitical ads.
3. Applying NLP and computer vision to extract several details such as content and category (attack vs promotion vs contrast) [Ref: Lei Qi.].
4. Analyzing the data to estimate the amount of spending, to clarify the user profiling, and so on.

Courses and TAships taken so far

Fall 2019:
1. STATS 542: Theory of probability and statistics-I. Being taught by: Prof Kris De Brabanter
2. COMS 527x: Concurrent Ssystem. Being taught by: Ali Jannesari. Course is not listed on iastate website. Description of the course is: Fundamentals and advances in concurrent systems in the context of GPUs, TPUs, multicore and HPC systems with specific focus on parallel programming models. Discussion of high-performance computing, GPGPU, scaling (ML/DL algorithms) deep neural network training, high-performance deep learning, engineering parallel software and parallel design patterns.
3. COMS 699: Thesis research under Prof Jin Tian.
4. RAship with Dr Adisak Sukul.
5. TAing COMS 228: Introduction to Data Structures. Being taught by: Prof Jim Lathrop
6. KIN 102: Swimming II. Being taught by ROSBURG, J
Summer 2019:
1. COMS 699: Thesis research under Prof Jin Tian.
2. RAship with Dr Adisak Sukul.
3. TAship: COMS 228: Introduction to Data Structures. Was taught by: Dr Georgi I. Batinov
Spring 2019:
1. COMS 511: Design and Analysis of Algorithms. Was taught by Prof David Fernández-Baca
2. COMS 634: Theory of Games, Knowledge and Uncertanity. Was taught by Prof Giora Slutzki
3. COMS 699: Thesis research under Prof Jin Tian.
4. STATS 543: Theory of probability and statistics-II. Was taught by: Prof Vivekananda Roy
5. TAship: COMS 311: Introduction to the Design and Analysis of Algorithms. Was taught by: Prof David Fernández-Baca and Prof Jia (Kevin) Liu.
Fall 2018:
1. COMS 699: Thesis research under Prof Jin Tian.
Spring 2018:
1. COMS 518: Computational Geometry. Was taught by Prof Yan-Bin Jia (贾燕斌)
2. COMS 531: Theory of Computation. Was taught by Prof Giora Slutzki
3. COMS 573: Machine Learning. Was taught by Prof Jin Tian
4. COMS 575: Computational Perception . Was taught by Alexander Stoytchev
  Involved a course project: For the project, I tried to do speech recognition using Shpinx. I downloaded video from CNBC TV 18, an Indian business and stock news channel. Extracted audio from it. Did transcription for few minutes and then tried to do it via Sphinx. I found that while distinguishing advertisement from news was fairly simple, speech recognition was dependent on speaker acoustic model, and was not good for all but one anchor. Creating individual speaker acoustic model was out of scope for the project.
5. TAship: COMS 228: Introduction to Data Structures. Was taught by: Prof Dossay Oryspayev
Fall 2017:
1. COMS 577: Problem Solving Techniques for Applied Computer Science, taught by Prof Yan-Bin Jia (贾燕斌)
2. COMS 511: Compulsory (and always fascinating) course: Design and Analysis of Algorithms, taught by Prof David Fernández-Baca
3. COMS 572: Artificial Intelligence, taught by Prof Jin Tian
  Involved a course project: Done with Sai Sahiti Nemalikanti. Jump here to see details.
4. COMS 592: Taught by Georgi I. Batinov
5. TA for COMS 227 Introduction to Object Oriented Programming (using Java) taken by Prof Steve Kautz and Prof Guang Song

Other Interests

My tryst with music (keyboard)

Music is an art, which may requires several lifetimes to learn. It's just some waves, some frequency of which whole world is composed of.

Dream to fly

My first skydiving. Sky Diving, is so under rated. The experience was so exhilarating that words can't do justice to it. It felt as if I am floating. It was also so peaceful and calm, literally top of the world experience. I could glide/fly in any direction I wanted.
This have, forever made me jealous of birds, who actually have wings and can fly. Sure we have airplanes and jet engines, but having ones own wings and flying ... well everything fades in front of that. Too bad we humans are so heavy... perhaps one day Elon Musk or someone will develop iron man suits.

Seeing the matrix: as it is

A bit of thought experiment would reveal that world is clearly not what it looks like. For example:

Second law of thermodynamics and expanding entropy of universe suggests that: The Universe has a beginning and time started sometime....
Since in theory we can always split things, thus, physical reality can not be physical..
Quantum computing is a reality, so a single qubit is in different state at the same time???

And yet, people don't bother to think about it and are busy living (whatever that means) and butchering innocent animals. I tried getting answers from religious practices but realized it is just another business (nothing more, IMHO). Vipassana meditation, in theory looks sound but who knows... Anyways I am actively practicing it and hope someday I'll be able to see the matrix.

Understanding physics is another way of doing it, (and I also do it (thanks to Coursera)), but my chances of contributing to that (or even understanding it completely) is slim to none. I do enjoy reading about relativity and quantum computing.

Done/Maintaining


2019 08 07	Updated my chrome extension: Annotate the web/CONTEXT I have updated it few times, still have not introduced my key idea of combining tasks and notes together. Before I could do that, I need to save annotation on gDrive. Someday...till then check it out and leave your feedback in the comments section.

2018 12 28	python3TCP. A simple code to demonstrate communication over TCP in python3. Please find the writeup here.

2017 12 04	Stock Market Prediction by web scraping: Crawled recommendation by CNBC, and applied a simple word2Vec model with stock movement around it. Achieved an impressive 30% annual return for past couple of years. Code can't be shared cause of efficient market hypothesis, as I am exploiting the niche. The project was done as part of 572 course project, and has been improved a lot after that. However, publicly available data as crawled from CNBC (stock recommendation: 2011 - Nov 2017) and NSE (stock prices: 2010 - Nov 2017) are available for download: CNBC Stock recommendation. NSE Stock prices (Only for 16 companies, data for all companies could be provided on request).

2017 11 06	A quick and dirty solution to share my PC screen to my eReader. I am doing lot's of reading and it would be good if I could do it without straining my eyes. Code shared https://github.com/aknirala/SharePCScreenshot.

2017 04 29	(ongoing) Some math, and ML concepts: Some basic math concepts. More to be added in time. Gaussian distribution. Exponential Family distribution. Some non-parametric methods

2017 04 24	Published my first chrome extension: Annotate Web pages This is the first version, I would be updating it to include many more features to it.

2017 03 23	Completed this course from Coursera: Understanding Einstein: The Special Theory of Relativity A write-up on this is here

2017 03 21	Completed CS 224D Assignment solutions here. https://github.com/aknirala/CS224D/ NN Forward and backward equation derivation here.

Other trivia


2019 06 28	Why We Sleep: Unlocking the Power of Sleep and Dreams. This was an amazing book. I always wondered, why rereading a paper many times in one seating didn't give me the kind of insights which I get when I read it after some time (days/weeks). As per book, during NREM sleep, day to day memories from hippocampus, are transferred to neocortex (permanent storage). This process is quite active and I believe some form of indexing ect also happens. Thus next time when we read the same thing we are making new connections which is often not possible, no matter how hard we try in the first go. Cracking this code completely would be awesome.

2017 04 29	Didn't knew that even, non-religious people are so much brain-washed. Why I escaped from my brainwashed country \| Hyeonseo Lee \| TEDxKyoto. What is the solution? Which policy should we make? What to do?

2017 03 21	This TED talk is amazing: The weirdness of water could be the answer \| Marcia Barbosa \| TEDxCER Just watch it at 1.5x. The enthusiasm with which she explains things, and of course the fluency comes from absolute control/knowledge of her research, simply made my day.