Derivative Convolutional Perceptron Acceleration — Derivative Convolutional Perceptron Separation
Descriptions may be stale. Consult the linked Lean sources.
Derivative Convolutional Perceptron Separation · Lean proof
Derivative Convolutional Perceptron Separation
We seek to separate samples
Equip the feature space
Our assumptions:
Assumption 1 (Background and derivative separation).
There exist scalars
Assumption 2 (Contrast scale). The contrast and
background scales satisfy
At any query
Proved result
OracleTemplate.Convergence LongTails.Setups.DerivativeConvolutionalPerceptron.spec
OracleTemplate.DerivativeConvolutionalPerceptron.budgetRelevant previous results
- A. Novikoff. On
Convergence Proofs for Perceptrons. 1963 proceedings; presented
1962. Complexity:
exact sample margin-and-gradient oracle calls for strict separation by cyclic perceptron, including a final verification pass, applied to features ; the proved perceptron update bound is for feature radius and separating margin .