Read the equation
A connection-weight change is scaled by a learning rate, a coherence-related factor, a signed difference between pre- and post-synaptic times, and an exponential timing factor. The sign depends on the source’s timing convention, which the poster does not define.
Its role in the build
The Megamind Equation Atlas
Terms & definitions
| Term | Meaning in this source |
|---|---|
| Δw_ij | change to connection weight from i to j |
| η | learning rate |
| t_pre | pre-synaptic event time |
| t_post | post-synaptic event time |
| τ | time scale |
How it works
Read Δw_ij as the quantity being defined or updated by this relation.
Applies an exponential factor. The exponent determines its real scaling or, for a complex exponent, its phase.
Use this version’s variable definitions and update order. The same symbol may be assigned a different meaning in another build.
Assumptions & limits
This single signed expression is a project variant, not the usual fully specified piecewise STDP rule. If Δt can be negative, exp(−Δt/τ) grows on that side; the poster supplies no absolute value, clipping or separate branch. C_ij and Φ require definitions.
Original context
Read the surrounding source passage
The Megamind Equation Atlas: A connection-weight change is scaled by a learning rate, a coherence-related factor, a signed difference between pre- and post-synaptic times, and an exponential timing factor. The sign depends on the source’s timing convention, which the poster does not define. Unified AGI Equation System: A connection-weight change is scaled by a learning rate, a coherence-related factor, a signed difference between pre- and post-synaptic times, and an exponential timing factor. The sign depends on the source’s timing convention, which the poster does not define.
Exact original notation
Δw_ij = η Φ(C_ij) (t_pre − t_post) exp(−Δt/τ)
Related builds
Sources & provenance
Δw_ij = η Φ(C_ij) (t_pre − t_post) exp(−Δt/τ)
Δw_ij = η Φ(C_ij) (t_pre − t_post) exp(−Δt/τ)