During a walking tour of Queensland’s Daintree rainforest in Australia, a talented guide regularly pointed out creatures that were well camouflaged into their surroundings. At one point, he directed our attention to a tree trunk, where a large grasshopper was camouflaged. The guide’s observations and stories wove together the connections between biology, geology and colonialism, helping explain how big and small changes could transform life in this ecosystem. Sometimes it’s difficult to see something, even when you’re staring directly at it. How many of us are aware of what’s hiding right in front of us?
Publication Details
Fan, Y., Tang, X., Zhou, G. & Shen, J. (2020). Efficient AutoGAN: Predicting the rewards in reinforcement-based neural architecture search for Generative Adversarial Networks. IEEE Transactions on Cognitive and Developmental Systems, online first 1-13.
Abstract
This paper is inspired by human’s memory and recognition process to improve Neural Architecture Search (NAS), which has shown novelty and significance in the design of Generative Adversarial Networks (GAN), but the extremely enormous time consumption for searching GAN architectures based on reinforcement learning (RL) limits its applicability to a great extent. The main reason behind the challenge is that, the performance evaluation of sub-networks during the search process takes too much time. To solve this problem, we propose a new algorithm, EfficientAutoGAN, in which a Graph Convolution Network (GCN) predictor is introduced to predict the performance of sub-networks instead of formally assessing or