Alert button
Picture for Noah Ford

Noah Ford

Alert button

Adaptive Neural Networks Using Residual Fitting

Jan 13, 2023
Noah Ford, John Winder, Josh McClellan

Figure 1 for Adaptive Neural Networks Using Residual Fitting
Figure 2 for Adaptive Neural Networks Using Residual Fitting
Figure 3 for Adaptive Neural Networks Using Residual Fitting
Figure 4 for Adaptive Neural Networks Using Residual Fitting

Current methods for estimating the required neural-network size for a given problem class have focused on methods that can be computationally intensive, such as neural-architecture search and pruning. In contrast, methods that add capacity to neural networks as needed may provide similar results to architecture search and pruning, but do not require as much computation to find an appropriate network size. Here, we present a network-growth method that searches for explainable error in the network's residuals and grows the network if sufficient error is detected. We demonstrate this method using examples from classification, imitation learning, and reinforcement learning. Within these tasks, the growing network can often achieve better performance than small networks that do not grow, and similar performance to networks that begin much larger.

* 10 pages, 9 Figures 
Viaarxiv icon