Hacker News Reader

iluvmylifeon Turning web design mockups into code with Deep Learning

This is great to see!

It's popular to apply AI to healthcare, transportation and legal work. However, these fields are heavily regulated, require domain expertise and data is hard to get. The nature of front-end dev and other digital skills make them more ripe for automation. I'm surprised there is so little progress in this area.

iluvmylifeon Why You Can Focus in a Coffee Shop but Not in Your Open Office

I have founds apps like Coffitivity [0] that simulate coffee shop banter extremely helpul with my productivity.

[0] https://coffitivity.com/

iluvmylifeon Generating six-pack abs with Tensorflow

Often times a body transformation from one image to another results in a redefinition of the relative position and length of edges in a photo (as a person gets leaner).

Do you think that the L1 regularization used in pix2pix - which is intended to preserve low-frequency spacial patterns in the image pairs - will ultimately end up limiting how well cGANs can learn the body transformation image translation task?

iluvmylifeon Tensorflow sucks

Tensorflow does do really well when it comes to serving models in production. Tensorflow serving or TensorRT 3 are fairly throughput efficient and low latency. PyTorch, for instance, does not have a good serving solution (I guess that's where Caffe2 is useful)

iluvmylifeon Colorizing black and white photos with deep learning

The averaging problem in colorization is interesting. If it learns that an apple can be red, green and even yellow - how does it know how to color it?

A HN user in an earlier thread suggested to use a fake/real colorization classifiers as a loss function. [1] But I still feel that it would not solve the averaging problem. It would hop between different colors and probably converge to brown. I haven’t come across a plausible solution so far. [1] https://news.ycombinator.com/item?id=10864801

iluvmylifeon Coding the History of Deep Learning

If you want a more nuanced research on the history on deep learning in neural networks, here is an excellent historical survey paper: https://arxiv.org/abs/1404.7828

iluvmylifeon Snowflake macro photography (2013)

I agree!

Going by the Bruce Lee quote "I fear not the man who has practiced 10,000 kicks once, but I fear the man who has practiced one kick 10,000 times". Only in this case kick = photography. There is definitely value in practicing a singular art with focus.

iluvmylifeon How I got to 200 productive hours a month

What did you use to create this? Anyone have good recommendation for mind map tools?

iluvmylifeon Your best passive income? (2014)

I made a super simple paid Android app with a list of interesting Physics Puzzles (https://play.google.com/store/apps/details?id=com.boredominn...). Took a month to make and now it is completely passive. Brings in some spare change with zero maintenance (~$50/month).

I built this in 2011 to learn app development (its a webapp built using PhoneGap). Took about a month of evening/weekend work to push out, and most of that time was consumed by collecting and creating interesting puzzles. It was featured on Google Play's Top Paid Educational Games leaderboard for a while, and that contributed to a spike in income. That apart, I haven't done/don't know of any viable means to promote it.