statementSaid on 2026-10-31
In a regular network, if the model errs, the backprop algorithm stops everything, goes back from end to start and updates all the weights; in the brain there is no such central manager, and instead each synapse learns on its own from its local environment using STDP.
A statement by author, said on 2026-10-31. Statements are as reported by the cited publishers — not verified by DecisionGateway.
ברשת רגילה, אם המודל טעה, אלגוריתם הבקפרופ עוצר הכל, חוזר אחורה מהסוף להתחלה ומעדכן את כל המשקולות. במוח אין "מנהל מרכזי" כזה. במקומו, כל חיבור בין שני נוירונים (סינפסה) לומד לבד מהסביבה הקרובה שלו בעזרת מנגנון תלוי-זמן הנקרא STDP
Discussion
Related claims
Each implanted layer is multiplied by a learned gate initialized to zero; at the moment of implantation the network does not change at all, and the gradient descent decides whether to open the gate.post author · statementLarge AI labs train models with MTP, but 80% of the gradient they backpropagate to the model is static noise that interferes with learning.post author · allegationDuring the backward pass, the MTP residual noise and the NTP residual noise meet with opposite signs and cancel each other out, leaving only the clean self-distillation signal; the result is 0 added memory, 0 impact on token throughput, and full compatibility with Fused kernels.post author · statementThe residual component is 4 times noisier than the first term, and is responsible for 80% of the update strength flowing back to the shared trunk; as the model grows it only intensifies and pulls the weights in a direction that interferes with next-token prediction.post author · statementThe book proves that unifying weights inside the attention mechanism to save memory erases the model's built-in ability to understand direction, order and causality.the post author · statementResearchers discovered long ago that about 75% of attention heads in a trained model can be deleted and it will keep working almost the same, and the book shows the structural reason: at the end of each layer the model merges all units' insights into one blend, so the next layer receives a 'fruit shake' and cannot know which unit discovered what.the post author · statement