Search Results for author:
Found 4 papers, 0 papers with code
Bayesian Attention Networks for Data Compression
Bayesian Attention Networks are defined by introducing an attention factor per a training sample loss as a function of two sample inputs, from training sample and prediction sample.
On Compression Principle and Bayesian Optimization for Neural Networks
Finding methods for making generalizable predictions is a fundamental problem of machine learning.
VARIATIONAL SGD: DROPOUT , GENERALIZATION AND CRITICAL POINT AT THE END OF CONVEXITY
Among stationary solutions of the update rules there are trivial solutions with zero variances at local minima of the original loss and a single non-trivial solution with finite variances that is a critical point at the end of convexity of the effective loss in the mean-variance space.
Continuous Learning: Engineering Super Features With Feature Algebras
We propose an iterative procedure for deriving a sequence of improving models and a corresponding sequence of sets of non-linear features on the original input space.
