"Underspecified and misaligned notions of interpretation impede progress towards the rigorous development of understandable, transparent, trusted AI systems."
Powerful thesis. Essentially these are the steps forward:
1. precise definitions of interpretation, yielding interp-metrics
2. develop and train models that optimize both prediction accuracy _and_ interp-metrics
1 comment
[ 3.5 ms ] story [ 11.4 ms ] threadPowerful thesis. Essentially these are the steps forward:
1. precise definitions of interpretation, yielding interp-metrics
2. develop and train models that optimize both prediction accuracy _and_ interp-metrics
3. voilà, aligned objectives yield trusted AI