Backprop Alternative: Augmented Lagrangian Predictive Coding

Re:Backprop Alternative: Augmented Lagrangian Predictive Coding by cs702 on Tuesday September 15, 2026 @05:42AM (#49709984)

"Backprop alternative" was the OP's headline.

I think my initial assessment is correct: interesting research, but not an alternative, at least not yet.

[ Parent | on HN ]

Re:Backprop Alternative: Augmented Lagrangian Predictive Coding by qarl on Tuesday September 15, 2026 @05:51AM (#49710046)

Ah. I missed that. Yeah. "Backprop alternative" is the wrong framing.

[ Parent | on HN ]

Re:Backprop Alternative: Augmented Lagrangian Predictive Coding by cs702 on Tuesday September 15, 2026 @07:32AM (#49710945)

Thanks. The exaggerated framing is the only reason why I posted my comment :-)

[ Parent | on HN ]