pith. sign in

Daniel Soudry

Identifiers

  • name variant Daniel Soudry 0.60 · backfill

Papers (32)

  1. Workspace Optimization: How to Train Your Agent cs.AI · 2026 · author #4
  2. Normalized Architectures are Natively 4-Bit cs.LG · 2026 · author #4
  3. Retrieval from Within: An Intrinsic Capability of Attention-Based Models cs.LG · 2026 · author #4
  4. Optimal L2 Regularization in High-dimensional Continual Linear Regression cs.LG · 2026 · author #5
  5. Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models stat.ML · 2019 · author #5
  6. How do infinite width bounded norm networks look in function space? cs.LG · 2019 · author #3
  7. Augment your batch: better training with larger batches cs.LG · 2019 · author #6
  8. Post-training 4-bit quantization of convolution networks for rapid-deployment cs.CV · 2018 · author #4
  9. Implicit Bias of Gradient Descent on Linear Convolutional Networks cs.LG · 2018 · author #3
  10. Scalable Methods for 8-bit Training of Neural Networks cs.LG · 2018 · author #4
  11. The Global Optimization Geometry of Shallow Linear Neural Networks cs.LG · 2018 · author #2
  12. Task Agnostic Continual Learning Using Online Variational Bayes stat.ML · 2018 · author #4
  13. Convergence of Gradient Descent on Separable Data stat.ML · 2018 · author #6
  14. Norm matters: efficient and accurate normalization schemes in deep networks stat.ML · 2018 · author #4
  15. On the Blindspots of Convolutional Networks stat.ML · 2018 · author #3
  16. Fix your classifier: the marginal value of training the last weight layer cs.LG · 2018 · author #3
  17. Train longer, generalize better: closing the generalization gap in large batch training of neural networks stat.ML · 2017 · author #3
  18. Exponentially vanishing sub-optimal local minima in multilayer neural networks stat.ML · 2017 · author #1
  19. Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations cs.NE · 2016 · author #3
  20. No bad local minima: Data independent training error guarantees for multilayer neural networks stat.ML · 2016 · author #1
  21. Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 cs.LG · 2016 · author #3
  22. Binarized Neural Networks cs.LG · 2016 · author #2
  23. Training Binary Multilayer Neural Networks for Image Classification using Expectation Backpropagation cs.NE · 2015 · author #2
  24. A structured matrix factorization framework for large scale calcium imaging data analysis q-bio.NC · 2014 · author #3
  25. Mean Field Bayes Backpropagation: scalable training of multilayer neural networks with binary weights stat.ML · 2013 · author #1
  26. A shotgun sampling solution for the common input problem in neural connectivity inference q-bio.NC · 2013 · author #1
  27. The neuron's response at extended timescales q-bio.NC · 2013 · author #1
  28. Spiking input-output relation for general biophysical neuron models q-bio.NC · 2012 · author #1
  29. An exact reduction of the master equation to a strictly stable system with an explicit expression for the stationary distribution q-bio.QM · 2012 · author #1
  30. Simple, Fast and Accurate Implementation of the Diffusion Approximation Algorithm for Stochastic Ion Channels with Multiple States q-bio.NC · 2011 · author #2
  31. Slow dynamics of neuronal excitability under pulse stimulation q-bio.CB · 2011 · author #1
  32. History dependent dynamics in a generic model of ion channels - an analytic study q-bio.SC · 2009 · author #1

Mentions

  • 1310.1867 #1 · backfill · confidence 0.70 Daniel Soudry
  • 1309.3724 #1 · backfill · confidence 0.70 Daniel Soudry
  • 1301.2631 #1 · backfill · confidence 0.70 Daniel Soudry
  • 1207.6251 #1 · backfill · confidence 0.70 Daniel Soudry
  • 1207.4436 #1 · backfill · confidence 0.70 Daniel Soudry
  • 1111.6062 #2 · backfill · confidence 0.70 Daniel Soudry
  • 1105.1275 #1 · backfill · confidence 0.70 Daniel Soudry
  • 0912.4060 #1 · backfill · confidence 0.70 Daniel Soudry

Frequent Coauthors