首页|New Artificial Intelligence Research from University of Electro-Communications D iscussed (Generative approaches for solving tangram puzzles)
New Artificial Intelligence Research from University of Electro-Communications D iscussed (Generative approaches for solving tangram puzzles)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators publish new report on ar tificial intelligence. According to news originating from the University of Elec tro-Communications by NewsRx editors, the research stated, “The Tangram is a dis section puzzle composed of seven polygonal pieces that can form different patter ns.” The news editors obtained a quote from the research from University of Electro-C ommunications: “Solving the Tangram is an irregular shape packing problem known to be NP-hard. This paper investigates the application of four deep-learning arc hitectures-Convolutional Autoencoder, Variational Autoencoder, U-Net, and Genera tive Adversarial Network-specifically designed for solving Tangram puzzles. We e xplore the potential of these architectures in learning the complex spatial rela tionships inherent in Tangram configurations. Our experiments show that the Gene rative Adversarial Network competes well with other architectures and converges considerably faster. We further prove that traditional evaluation metrics based on pixel accuracy often fail in assessing the visual quality of the generated Ta ngram solutions. We introduce a loss function based on a Weighted Mean Absolute Error that prioritizes pixels representing inter-piece sections over those cover ed by individual pieces.”
University of Electro-CommunicationsAr tificial IntelligenceMachine Learning
NETL
NSTL
