A Quantitative Approach to Predicting Representational Learning and Performance in Neural Networks
This work addresses the challenge of understanding and designing neural networks for researchers, but it appears incremental as it builds on existing analysis methods.
The authors tackled the problem of predicting how neural networks learn representations by introducing a pseudo-kernel based tool that analyzes initial conditions and training curriculum, and they demonstrated its ability to predict effects on representational learning and concurrent multitasking performance.
A key property of neural networks (both biological and artificial) is how they learn to represent and manipulate input information in order to solve a task. Different types of representations may be suited to different types of tasks, making identifying and understanding learned representations a critical part of understanding and designing useful networks. In this paper, we introduce a new pseudo-kernel based tool for analyzing and predicting learned representations, based only on the initial conditions of the network and the training curriculum. We validate the method on a simple test case, before demonstrating its use on a question about the effects of representational learning on sequential single versus concurrent multitask performance. We show that our method can be used to predict the effects of the scale of weight initialization and training curriculum on representational learning and downstream concurrent multitasking performance.