Back again after a long hiatus

It’s been almost an entire year since I’ve updated my blog– and my has it been an eventful year. Ever since I last posted here, I completed a 3 month industry internship with one of the largest data science teams in industry Stitch Fix, and accepted a fellowship at the NYU Center for Data Science and NYU Center for Cosmology and Particle Physics.

Read More

Placed 15th in an algorithmic stock trading competition

For those who know me personally, it’s no secret that I enjoy economics and financial analysis. For this reason I was pretty excited when I discovered the Quantopian platform/website (quantopian.com) about 8 months ago or so. Quantopian is great, and if you’ve ever considered algorithmic stock trading, I highly suggest looking into it. Effectively, quantopian provides a python platform and a convenient interface to minutely pricing data on public companies traded within the United States.

Read More

Predicting discoveries part 1

I’ve been working on a problem recently that I think is a rather interesting application of machine learning. Unfortunately I cannot give too many specifics as the algorithm I’ve developed is currently being used in two papers that are about to be submitted for publication. When they are submitted though, I will most definitely give a well describe tutorial here!

Read More

So much data, so little time

Things have been good lately in the research front. Much progress on quite a few projects– been multi-threading since I got to Vanderbilt in various fields. I’m pretty excited to see a few papers I’ve been working on well outside of my comfort zone almost complete. Never did I think two years ago that I would be working on exoplanet statistics, machine learning or struggling with pandas data frames (I hate you pandas).

Read More

Relaxxxiinnnnn'

Well, I haven’t updated in quite some time, been extremely busy with many applications and papers, but glad to be back!

Read More

Statistical mechanics of learning networks

I haven’t updated the research blog in sometime since I’ve been exceptionally busy, yet even more than usual, considering I’ve been submitting applications for various fellowships and preparing for the Ted talk. I can’t wait until November 17th; my life may actually slow down considerably!

Read More

Deep Believe Networks and Statistical Mechanics

Read an amazing paper today by I. P. Waldmann: Dreaming of atmospheres on deep belief networks and an application to predicting exoplanet atmospheric content from spectral data. For me it kills two birds with one paper– my friends Duane Lee and Mike Lund and I have hit a bottleneck on a paper we’re currently working on, where we have not been able to, with reasonable computaional time, extract meaningful atmospheric chemical information from spectral emissions from exoplanets. This paper proposes a way of getting around this issue using a deep believe network to predict chemical species from spectral information as input; it’s genuis. I’ll probably email the guys after this post to let them know we can move past this road block.

Read More

Hankel functions, BBN, waterfall mechanisms in inflation and the NFL.

Today was a pretty busy day. Started out the morning by working with graduate students who I tutor biweekly on math methods. They have an exam coming up this Friday and are pretty nervous about it. I’m glad I somehow still remember all sort of random orthonormality conditions for obscure special functions..!

Read More