Human-level performance via ML was *not* proven impossible with complexity theory [D]

“`html

• A paper claiming to have proven that achieving human-level performance via machine learning (ML) is impossible has been refuted by a new study.
• The original research, published in Computational Brain & Behavior, presented what they called the “Ingenia Theorem.” However, this theorem relies on undefined terms and logical leaps, which can be easily misinterpreted or manipulated.
• Key issues identified include the lack of a clear mathematical definition for “human-level classifier” and how this term changes when used theoretical proof is constructed.

“`

Stay ahead of AI. Get the most important stories delivered to your inbox — no spam, no noise.

Please enable JavaScript in your browser to complete this form.

Name *

First

Last

Email Name

Email *

Submit