Publications (28)
Convergence of Gradient Descent on Separable Data
Mor Shpigel Nacson, Jason D. Lee, Suriya Gunasekar +3
The neuron's response at extended timescales
Daniel Soudry, Ron Meir
Scalable Methods for 8-bit Training of Neural Networks
Ron Banner, Itay Hubara, Elad Hoffer +1
Task Agnostic Continual Learning Using Online Variational Bayes
Chen Zeno, Itay Golan, Elad Hoffer +1
A shotgun sampling solution for the common input problem in neural connectivity inference
Daniel Soudry, Suraj Keshri, Patrick Stinson +3
Post-training 4-bit quantization of convolution networks for rapid-deployment
Ron Banner, Yury Nahshan, Elad Hoffer +1
Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models
Mor Shpigel Nacson, Suriya Gunasekar, Jason D. Lee +2
A structured matrix factorization framework for large scale calcium imaging data analysis
Eftychios A. Pnevmatikakis, Yuanjun Gao, Daniel Soudry +6
Slow dynamics of neuronal excitability under pulse stimulation
Daniel Soudry, Ron Meir
Training Binary Multilayer Neural Networks for Image Classification using Expectation Backpropagation
Zhiyong Cheng, Daniel Soudry, Zexi Mao +1
An exact reduction of the master equation to a strictly stable system with an explicit expression for the stationary distribution
Daniel Soudry, Ron Meir
Train longer, generalize better: closing the generalization gap in large batch training of neural networks
Elad Hoffer, Itay Hubara, Daniel Soudry
Augment your batch: better training with larger batches
Elad Hoffer, Tal Ben-Nun, Itay Hubara +3
Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
Matthieu Courbariaux, Itay Hubara, Daniel Soudry +2
Implicit Bias of Gradient Descent on Linear Convolutional Networks
Suriya Gunasekar, Jason Lee, Daniel Soudry +1
Mean Field Bayes Backpropagation: scalable training of multilayer neural networks with binary weights
Daniel Soudry, Ron Meir
History dependent dynamics in a generic model of ion channels - an analytic study
Daniel Soudry, Ron Meir
Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
Itay Hubara, Matthieu Courbariaux, Daniel Soudry +2
Fix your classifier: the marginal value of training the last weight layer
Elad Hoffer, Itay Hubara, Daniel Soudry
Exponentially vanishing sub-optimal local minima in multilayer neural networks
Daniel Soudry, Elad Hoffer
Spiking input-output relation for general biophysical neuron models
Daniel Soudry, Ron Meir
How do infinite width bounded norm networks look in function space?
Pedro Savarese, Itay Evron, Daniel Soudry +1
No bad local minima: Data independent training error guarantees for multilayer neural networks
Daniel Soudry, Yair Carmon
Binarized Neural Networks
Itay Hubara, Daniel Soudry, Ran El Yaniv
Simple, Fast and Accurate Implementation of the Diffusion Approximation Algorithm for Stochastic Ion Channels with Multiple States
Patricio Orio, Daniel Soudry
On the Blindspots of Convolutional Networks
Elad Hoffer, Shai Fine, Daniel Soudry
Norm matters: efficient and accurate normalization schemes in deep networks
Elad Hoffer, Ron Banner, Itay Golan +1
The Global Optimization Geometry of Shallow Linear Neural Networks
Zhihui Zhu, Daniel Soudry, Yonina C. Eldar +1