University Research Co (United States)

Channel widths in a lightweight medical image classifier no longer have to be set by hand or found by architecture search. Fibonacci-Net allocated filters by a fixed second-order recurrence, leaving little control over capacity. Scaled m-BonacciNet derives a scaling coefficient from the dominant root of the m-Bonacci recurrence, narrows the original channel vector, and uses depthwise separable convolutions in the last blocks; on 15-class brain MRI, the Tribonacci variant reached 96.09% accuracy and 0.9581 macro F1 with about 0.85 million parameters and 365.69 million FLOPs, though some variants lost accuracy on 4-class brain MRI and CKD ultrasound.

Channel widths in a lightweight medical image classifier no longer have to be set by hand or found by architecture search. Fibonacci-Net allocated filters by a fixed second-order recurrence, leaving little control over capacity. Scaled m-BonacciNet derives a scaling coefficient from the dominant root of the m-Bonacci recurrence, narrows the original channel vector, and uses depthwise separable convolutions in the last blocks; on 15-class brain MRI, the Tribonacci variant reached 96.09% accuracy and 0.9581 macro F1 with about 0.85 million parameters and 365.69 million FLOPs, though some variants lost accuracy on 4-class brain MRI and CKD ultrasound.