today I started learning about artificial intelligence and machine learning in tensor flow. I did not know what a logit was so I looked up some videos explaining it. My understanding of it is that it is the inverse of a logistical function. it is useful in probabilities because it approaches infinity at 0 and 100 percent probable. This mirrors actual probability in that typically one cannot be certain about anything (meaning certainly false or certainly true) and that it is substantially harder to increase probability from 70 to 90 vs 50 to 70.
barrett_j
Comments