Why "Good" Research Ideas Fail

One day in my life as a machine learning researcher, I had a new idea, and it felt like a good idea. I had a rush of excitement, but then… some hesitation. As always, I knew that having an idea that feels good is different from having an idea that's actually good. The ultimate test of whether an idea is actually good is to see if it works in the real world. Testing in the real world, though, requires careful implementation and experimentation.