Knowledge Evolution in Neural Networks

The optimization manifold for a deep network has many local minima. With a small dataset, the deep network is likely to fall into an inferior local minimum. Within a local minimum, the gradient is zero. Accordingly, gradient descent cannot get the network out. Knowledge evolution (KE) splits the network into two parts and re-initializes one part randomly. Hopefully, this gets the network out of the inferior local minimum. Then, KE resumes training — using gradient descent — to evolve the knowledge inside the network.
KE splits a deep network into two parts: fit-hypothesis (blue) and reset-hypothesis (gray). KE re-initializes the reset-hypothesis when the network overfits, i.e., enters an inferior local minimum. After re-initialization, the network resumes training using gradient descent. Gradient descent evolves the knowledge inside the fit-hypothesis.
After training a network for e epochs, KE reinitializes the reset-hypothesis. Then, KE trains the next generations iteratively.
Classification performance on Flower-102 (FLW) and CUB-200 (CUB) datasets trained on a randomly initialized ResNet18. The horizontal dashed lines denote a SOTA cross-entropy (CE) baseline [2]. The marked curves show KE’s performance across generations.
Quantitative classification evaluation using CUB-200 on VGG11-bn. The x-axis denotes the number of generations. The fit-hypothesis (blue dotted curve) achieves an inferior performance at g = 1, but its performance increases as the number of generations increases.
Quantitative evaluation for KE using the number of both operations (G-Ops) and parameters (millions). Acc_g denotes the classification accuracy at the g-th generation. \triangle_ops denotes the relative reduction in the number of operations. \triangle_acc denotes the absolute accuracy improvement on top of the dense baseline N1.



Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Ahmed Taha

Ahmed Taha

I write reviews on computer vision papers. Writing tips are welcomed.