Viewing profile — ramanan

True. I’m no expert in this area, but there are a lot more factors too - including territorial range and even different camera locations.

This catch and release pattern is quite common in many wildlife surveys. For example, when estimating tiger populations, instead of painting a white dot, rangers set up camera trap…

This downward trend has long been in the works. The current government came into power riding on a wave of popularity, largely driven by their "IT cells". Now comfortably in power,…

Spotting a distressed swimmer is possibly much harder than most people expect. There is a great website where you can try your spotting skills yourself [1]. [1] http://spotthedrown…

minutephysics had a nice video about the mathematics that go behind piano tuning too. "Why It's Impossible to Tune a Piano" https://www.youtube.com/watch?v=1Hqm0dYKUx4

Got it. I was looking for input on how generalizable (the ability of weights to change/adapt) when the training labeled data is 100x smaller than the initial pre-training dataset? …

I understand that you do mention the pre-training / transfer learning approach clearly, but isn't it disingenuous to claim that you provide better performance based on (only) 100 l…

Well, one easy way when using Ubuntu-like distributions is to simply place your `/home` folder on a separate (persistent) EBS volume [1]. With a few on-boot scripts to attach-volum…

there are a number of similar paradoxes that arise when considering infinities of different sizes! Infinity Paradoxes - Numberphile - https://www.youtube.com/watch?v=dDl7g_2x74Q