Continuously Constructive Deep Neural Networks
This work addresses the challenge of architecture selection in deep learning, which is incremental as it builds on existing methods by automating structure updates.
The authors tackled the problem of manually selecting neural network architectures by proposing two methods that automatically update network structure and weights simultaneously, demonstrating effectiveness on synthetic and real datasets including MNIST and MIRFLICKR with adaptive complexity.
Traditionally, deep learning algorithms update the network weights whereas the network architecture is chosen manually, using a process of trial and error. In this work, we propose two novel approaches that automatically update the network structure while also learning its weights. The novelty of our approach lies in our parameterization where the depth, or additional complexity, is encapsulated continuously in the parameter space through control parameters that add additional complexity. We propose two methods: In tunnel networks, this selection is done at the level of a hidden unit, and in budding perceptrons, this is done at the level of a network layer; updating this control parameter introduces either another hidden unit or another hidden layer. We show the effectiveness of our methods on the synthetic two-spirals data and on two real data sets of MNIST and MIRFLICKR, where we see that our proposed methods, with the same set of hyperparameters, can correctly adjust the network complexity to the task complexity.