You May Also Enjoy
APSP on GPU
13 minute read
Published:
The Floyd-Warshall Algorithm Re-implemented Using 3D-Tensors and Hardware Acceleration
Author: Taher Anjary
Learning Locomotion
10 minute read
Published:
Imagine you were given a hexapod- a six legged robot that kind of looks like a cyborg spider. And someone asks you to program it to walk. Your first though might be to use a bunch of trigonometric formulae to control each of its joints. Such an approach is hard-coded, difficult to design (believe me, I’ve tried), and your hexapod would not be able to adapt very well to changing terrain or speed- or at least, it would not look very organic. Fortunately, we live in an age where artificial intelligence can do the thinking for us. Described below are 3 methods that could be used to train a robot to move and balance itself as though it were real!
Collaborative Approaches in AI
5 minute read
Published:
I believe that in order for a system to be successful in large scale contexts, the system must learn to collaborate. The idea makes sense considering how the human species dominated the earth because we learnt to cooperate. We see this in nature as well; Packs of wolves and prides of lions learnt to hunt together as teamwork proved to be more efficient and effective. Ant colonies can join themselves to form bridges or rafts when faced with appropriate obstacles. Amazing! Don’t you think?
Blog Post number 4
less than 1 minute read
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.