# Gradual DropIn of Layers to Train Very Deep Neural Networks

Source: [Gradual DropIn of Layers to Train Very Deep Neural Networks](<https://www.sota2.com/research/paper/68fa622b1e209131ce9f7d70>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:13:30.351Z

Authors: Leslie N. Smith, Emily M. Hand, Timothy Doster

Published: 2015-11-22T02:33:08.000Z

## Abstract

We introduce the concept of dynamically growing a neural network during training. In particular, an untrainable deep network starts as a trainable shallow network and newly added layers are slowly, organically added during training, thereby increasing the network's depth. This is accomplished by a new layer, which we call DropIn. The DropIn layer starts by passing the output from a previous layer (effectively skipping over the newly added layers), then increasingly including units from the new layers for both feedforward and backpropagation. We show that deep networks, which are untrainable with conventional methods, will converge with DropIn layers interspersed in the architecture. In addition, we demonstrate that DropIn provides regularization during training in an analogous way as dropout. Experiments are described with the MNIST dataset and various expanded LeNet architectures, CIFAR-10 dataset with its architecture expanded from 3 to 11 layers, and on the ImageNet dataset with the AlexNet architecture expanded to 13 layers and the VGG 16-layer architecture.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1511.06951>)

[PDF](<https://arxiv.org/pdf/1511.06951.pdf>)