Javier Sagastuy
Javier Sagastuy
Home
Publications
Paper Read Log
Experience
Light
Dark
Automatic
Page not found
Perhaps you were looking for one of these?
Latest
Inter-animal transforms as a guide to model-brain comparison
Recurrent Connections in the Primate Ventral Visual Stream Mediate a Trade-Off Between Task Performance and Network Size During Core Object Recognition
Limiting Dynamics of SGD: Modified Loss, Phase Space Oscillations, and Anomalous Diffusion
Generalized Shape Metrics on Neural Representations
Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics
Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks
A Variational Analysis of Stochastic Gradient Algorithms
Three Factors Influencing Minima in SGD
Spherical Motion Dynamics of Deep Neural Networks with Batch Normalization and Weight Decay
Two Routes to Scalable Credit Assignment without Weight Symmetry
Cite
×