diff options
Diffstat (limited to 'results/figs/main_figure_captions.md')
| -rw-r--r-- | results/figs/main_figure_captions.md | 11 |
1 files changed, 11 insertions, 0 deletions
diff --git a/results/figs/main_figure_captions.md b/results/figs/main_figure_captions.md index 899fadf..03c16c8 100644 --- a/results/figs/main_figure_captions.md +++ b/results/figs/main_figure_captions.md @@ -22,3 +22,14 @@ depth and initialization seed. **c,** Mean per-sample cosine between the teachin descent direction, averaged over the earliest third of hidden layers. Exact gradients are used only for this diagnostic, never for local learning. “Scaling” here means preserving useful accuracy and credit assignment as depth grows; flattened-CIFAR accuracy itself does not increase with depth. + +**Figure 3 | Somato-dendritic innovation is necessary under predictable apical traffic.** Mean ± +sample standard deviation across five seeds on MNIST, using depth-3, width-256 networks for 15 +epochs. **a,** The raw apical compartment mixes causal feedback with ordinary traffic predictable +from the same neuron's somatic state. SDIL subtracts the neutral-period per-cell prediction and +uses only the innovation in the local eligibility update. **b,** Test accuracy as predictable +traffic increases. The norm-matched raw control has the innovation's per-sample magnitude but +retains the raw direction. **c,** Final cosine between the signal actually used for learning and +the exact negative hidden-state gradient, averaged over all hidden layers. Exact gradients are +diagnostic only. At `rho=0.5`, raw and norm-matched raw feedback reach chance while innovation +retains `97.35%` accuracy and positive descent alignment. |