Deep learning models have proven to be exceptionally useful in performing many machine learning tasks. However, for each new dataset, choosing an effective size and structure of the model can be a time-consuming process of trial and error. While a small network with few neurons might not be able to capture the intricacies of a given task, having too many neurons can lead to overfitting and poor generalization. Here, we propose a practical method that employs matrix conditioning to automatically design the structure of layers of a feed-forward network, by first adjusting the proportion of neurons among the layers of a network and then scaling the size of network up or down. Results on sample image and non-image datasets demonstrate that our method results in small networks with high accuracies. Finally, guided by matrix conditioning, we provide a method to effectively squeeze models that are already trained. Our techniques reduce the human cost of designing deep learning models and can also reduce training time and the expense of using neural networks for applications.
Revisiting Initializing Then Refining: An Incomplete and Missing Graph Imputation Network
National University of Defense Technology（国防科技大学）；Chongqing University of Posts and Telecommunications（重庆邮电大学）；Hainan University（海南大学）；Hainan blockchain technology engineering research center（海南区块链技术工程研究中心）
Novel sparse matrix algorithm expands the feasible size of a self-organizing map of the knowledge indexed by a database of peer-reviewed medical literature
James Cook University（詹姆斯·库克大学）；University of Newcastle（纽卡斯尔大学）
On the emergence of numerical instabilities in Next Generation Reservoir Computing
Department of Electrical and Computer Engineering, Clarkson University, Potsdam, 13699, New York, U.S.A.（电气与计算机工程系，克林顿大学）；Clarkson Center for Complex Systems Science, Clarkson University, Potsdam, 13699, New York, U.S.A.（复杂系统科学中心，克林顿大学）
Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks
Elmore Family School of Electrical and Computer Engineering（埃尔莫尔电气与计算机工程学院）；Purdue University（普渡大学）；Department of Physics and Astronomy（物理与天文学系）；Halıcıoğlu Data Science Institute（哈利奇奥格卢数据科学研究所）；University of California San Diego（加州大学圣地亚哥分校）；Rosen Center For Advanced Computing（罗森先进计算中心）
Semi-Supervised Clustering via Dynamic Graph Structure Learning
Yau Mathematical Sciences Center, Tsinghua University（清华大学丘成桐数学科学中心）；Yanqi Lake Beijing Institute of Mathematical Sciences and Applications（北京雁栖湖应用数学研究院）
