News for hackers. Stuff that matters.

A comment on Tesla Model 3 Drives into Overturned Truck in Apparent Autopilot Failure. Parent comment

Re:Tesla Model 3 Drives into Overturned Truck in Apparent Au... by viraptor on Monday June 01, 2020 @07:58PM (#23385561)
> to make it one-log better you need 100x the data and 100x the NN dimensionality.

I'm not sure why you think so. At some point the dimensions will get diminishing returns. Maybe you need only 100x the data at this point (or maybe not). But assuming it's both without knowing the current configuration / limits is just a random guess.

[ Parent | on HN ]
Re:Tesla Model 3 Drives into Overturned Truck in Apparent Au... by s1artibartfast on Monday June 01, 2020 @08:32PM (#23385808)
Isnt the point that you have to get deep into the diminishing returns to root out extremely rate errors?
[ Parent | on HN ]
Re:Tesla Model 3 Drives into Overturned Truck in Apparent Au... by viraptor on Tuesday June 02, 2020 @05:03AM (#23389119)
Not always. Sometimes the fix may be just to add some teaching samples you haven't seen before and the NN is already capable of handling.
[ Parent | on HN ]