"Lessons for the young man"

  Oh you gonna lie, my boy
  You gonna use some cheap tears and cry
  Just know, it is okay to lie

  Oh you gonna lose, my boy
  You will, again and again
  Just know it is okay to cry

  Dreams go awry, my boy
  You will hit the rock bottom
  Just know we all have been there

  Look around, fun is over
  You will soon start day in and day out
  Just know it is okay to go slower

  'What is the point', don't ask my boy
  We know none the better
  Just create your own bubble soon, we will join
 

Watering the plastic plants

Don't want to watch the birds and the bees
He knows not the sounds of rains and seas
Never knew how the flowers smell
or even how the rivers swell

Ain't got no time, because he is busy
watering the plastic plants

She heard that critters are dying
long gone are the many birds, they say
There is little hope, if at all
Don't know if kids would play in the woods again

Ain't got no time to think, because she is busy
watering the digital plants

We still hear about the kids in Africa
or the bombs in Syria
But it ain't our problem you see
those seem so far away

Ain't got no time to worry, because we are busy
watering the plastic plants

30DaysML: Day25

I started with trying to understand this implementation of RNN, which involves some language modelling. Soon I had to go back to understand basics!

So I watched few hours of Oxford lessons here, more precisely the Lecture 3 and 4. Way better introduction to language modelling than other tutorials I've seen so far.

Must not lose focus! 

 

30DaysML: Day24

I went back to TensorFlow tutorials. Since I still don't get high level APIs, I figured best way is to understand these smaller programs and play around with them. 

Also, got completely distracted by some climate change reports, then spent time day dreaming about end of the world. Not productive, Harsha.

30dayML: Day20

Spent quite a bit of time re-writing / adjusting my cat-or-dog CNN network. Now I have an easy way to feed images to the model. Accuracy is still less than 50% though. Hyper-parameter tuning, here I come!

On a side note: Now I see why I should have GPUs. Each run takes 30 to 60 minutes. 

Once I do get to some acceptable accuracy (>90%), I'll move on to RNNs and Voice recognition. Although I still don't know much about Tensorflow high level APIs. OR should I learn Keras? Uggh.

Mood: Sherlock Holmes