Math is beautiful. Our education system does not often reveal this. It's a lost opportunity to inspire creative young minds who are captivated by the incredible mysteries of our universe.
@DaleSteyn62 Machine measurements are not 100% accurate. There will always be delta error. So if the ball is hitting marginally and if you add delta error to that, it could go either way. So you go umpire's guts in that case.
In 2019, may your:
- Pre-trained models transfer well
- Batch size be just right
- Architecture Search find effective networks
- RL not be hindered by simulation artifacts
- Conferences be all inclusive
- AI forever be non-sentient
Happy New Year Everyone! 🎉🌎🍾🥂😃
A Beginner’s Guide to the Mathematics of Neural Networks: a non-expert guide. Originally published in 1998 and totally missing all deep networks of today, but very relevant nonetheless. https://t.co/fwKpACRjYq
Dada and The Wall - Ganguly and Dravid. What a pair! 🙌
On this month's Legends' Corner they look back at the great moments of their relationship, from the origins in the eighties, to that famous @cricketworldcup partnership and beyond.
“Basically, if you want to do a NLP task, no matter what it is, what you should do is throw your data into a bi-directional long-short term memory network, and augment its information flow with attention mechanism.” - @chrmanning