We present a framework for discriminative sequence classification where the learner works directly in the high dimensional predictor space of all subsequences in the training set. This is possible by employing a new coordinate-descent algorithm coupled with bounding the magnitude of the gradient for selecting discriminative subsequences fast. We characterize the loss functions for which our generic learning algorithm can be applied and present concrete implementations for logistic regression (binomial log-likelihood loss) and support vector machines (squared hinge loss). Application of our algorithm to protein remote homology detection and remote fold recognition results in performance comparable to that of state-of-the-art methods (e.g., kernel support vector machines). Unlike state-of-the-art classifiers, the resulting classification models are simply lists of weighted discriminative subsequences and can thus be interpreted and related to the biological problem.
Semi-supervised structured output prediction by local linear regression and sub-gradient descent
King Abdullah University of Science and Technology(阿卜杜拉国王科技大学);Vanderbilt University(范德堡大学);Suning Commerce R&D Center USA, Inc(苏宁美国研发中心);Beijing Jiaotong University(北京交通大学);New York University Abu Dhabi(纽约大学阿布扎比分校);National Time Service Center, Chinese Academy of Sciences(中国科学院国家授时中心);Graduate University of Chinese Academy of Sciences(中国科学院研究生院)
Predicting gene essentiality and drug response from perturbation screens in preclinical cancer models with LEAP: Layered Ensemble of Autoencoders and Predictors
When majority rules, minority loses: bias amplification of gradient descent
University of Lille(里尔大学);Toulouse School of Economics(图卢兹经济学院);Institut Universitaire de France (IUF)(法国大学研究院(IUF));ANITI;Université de Toulouse(图卢兹大学);INRIA(法国国家信息与自动化研究所)
Antifragility Predicts the Robustness and Evolvability of Biological Networks through Multi-class Classification with a Convolutional Neural Network
University of Copenhagen(哥本哈根大学);Graz University of Technology(格拉茨工业大学);Sorbonne Université(索邦大学);Universidad Nacional Autónoma de México(墨西哥国立自治大学);ITMO University(ITMO大学)
A novel multivariate performance optimization method based on sparse coding and hyper-predictor learning
School of Electronic Information Engineering, Tianjin University, Tianjin 300072, China(电子信息工程学院,天津大学);College of Information Science and Technology, University of Nebraska Omaha, Omaha, NE 68182,United States(信息科学与技术学院,内布拉斯加大学奥马哈分校)
A Fast Screening Approach for High-dimensional Outcomes and High-dimensional Predictors
School of Pharmacy, University of North Carolina, Chapel Hill(北卡罗来纳大学药学院);Maryland Psychiatric Research Center, School of Medicine, University of Maryland(马里兰大学医学院精神病研究中心)
In-Context Learning can distort the relationship between sequence likelihoods and biological fitness
Computational Biology and Bioinformatics Program(计算生物学与生物信息学项目);Emeritus Department of Ecology and Evolutionary Biology(退休生态学与进化生物学系);Department of Evolutionary Biology(进化生物学系);Hagler Institute for Advanced Studies(哈格勒高级研究 institute);Department of Physics(物理学系);Quantitative Biology Institute(定量生物学研究所)
Quadratic integrate-and-fire neurons exhibit less fragmented loss landscapes and outperform leaky integrate-and-fire neurons in spike-based gradient descent
University of Bonn(波恩大学);University of Tübingen(图宾根大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
Institute for Stochastics(随机学研究所);Applications, University of Stuttgart(应用,斯图加特大学);School of Mathematical Sciences(数学科学学院);Institute of Natural Sciences(自然科学研究所);MOE-LSC, Shanghai Jiao Tong University(教育部-上海交通大学联合实验室)
Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neural Networks without Weight Symmetry
Gatsby Computational Neuroscience Unit, UCL(伦敦大学学院盖茨比计算神经科学单元);KUIS AI Center, Koc University(科奇大学KUIS人工智能中心);EEE Department, Koc University(科奇大学电气与电子工程系);John A. Paulson School of Engineering & Applied Sciences and Center for Brain Science, Harvard University(哈佛大学约翰·A·保尔森工程与应用科学学院及脑科学中心);Kempner Institute for the Study of Natural and Artificial Intelligence(肯普纳自然与人工智能研究所)