vix.ing · top · new · best · stats · spec

Leslie N. Smith

  1. A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay
    2018/03/26 by Leslie N. Smith, Smith, Leslie N. · 24 citations
    Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE)
  2. Super-Convergence: Very Fast Training of Neural Networks Using Large\n Learning Rates
    2017/08/23 by Leslie N. Smith, Nicholay Topin, Smith, Leslie N. +1 · 10 citations
    Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and ELM #Neural and Evolutionary Computing (cs.NE) #Stochastic Gradient Optimization Techniques
  3. Best Practices for Applying Deep Learning to Novel Applications
    2017/04/05 by Leslie N. Smith, Smith, Leslie N. · 1 voice
    Computer Science · Social Sciences · #Anomaly Detection Techniques and Applications #Software Engineering and Design Patterns #Time Series Analysis and Forecasting #cs.AI #cs.NE #cs.SE
  4. Gradual DropIn of Layers to Train Very Deep Neural Networks
    2015/11/22 by Leslie N. Smith, Smith, Leslie N., Emily M. Hand +3 · 1 citation
    Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #cs.CV #cs.LG #cs.NE