The 2022 AI Index
The Data Exchange with Ben Lorica
00:00
Benchmarking Benchmarks in Computer Vision
In some areas, it's just hard to create bench marks because there's no consensus of how to measure things. Another area where it's challenging is rabotic rightf if i have one robot in one lab and a different robot in another lab. Annatually figuring out how to evaluate them together is the ser challenger.
Transcript
Play full episode
