TFCheck : A TensorFlow Library for Detecting Training Issues in Neural Network Programs. (arXiv:1909.02562v1 [cs.LG])

DeepEvolution: A Search-Based Testing Approach for Deep Neural Networks. (arXiv:1909.02563v1 [cs.LG])

Classification with Costly Features as a Sequential Decision-Making Problem. (arXiv:1909.02564v1 [cs.LG])

Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agents. (arXiv:1909.02583v1 [cs.LG])

Additive function approximation in the brain. (arXiv:1909.02603v1 [cs.NE])

A Bayesian Approach to Multiple-Output Quantile Regression. (arXiv:1909.02623v1 [stat.ME])

Diversely Stale Parameters for Efficient Training of CNNs. (arXiv:1909.02625v1 [cs.LG])

Changepoint analysis of historical battle deaths. (arXiv:1909.02626v1 [stat.AP])

Contextual Minimum-Norm Estimates (CMNE): A Deep Learning Method for Source Estimation in Neuronal Networks. (arXiv:1909.02636v1 [q-bio.QM])

Intensity augmentation for domain transfer of whole breast segmentation in MRI. (arXiv:1909.02642v1 [eess.IV])

On perfectness in Gaussian graphical models. (arXiv:1909.01978v1 [math.ST])

Quasi-Newton Optimization Methods For Deep Learning Applications. (arXiv:1909.01994v1 [cs.LG])

Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning. (arXiv:1909.02005v1 [astro-ph.CO])

Bayesian Inference of Networks Across Multiple Sample Groups and Data Types. (arXiv:1909.02058v1 [stat.ME])

DCGANs for Realistic Breast Mass Augmentation in X-ray Mammography. (arXiv:1909.02062v1 [eess.IV])

Diversity Breeds Innovation With Discounted Impact and Recognition. (arXiv:1909.02063v1 [cs.SI])

On Least Squares Estimation under Heteroscedastic and Heavy-Tailed Errors. (arXiv:1909.02088v1 [math.ST])

Gradients of Generative Models for Improved Discriminative Analysis of Tandem Mass Spectra. (arXiv:1909.02093v1 [q-bio.QM])

Accelerated Information Gradient flow. (arXiv:1909.02102v1 [math.OC])

Meta Learning with Relational Information for Short Sequences. (arXiv:1909.02105v1 [cs.LG])

Show more
QOTO Mastodon

QOTO: Question Others to Teach Ourselves. A STEM-oriented instance.

No hate, No censorship. Be kind, be respectful

We federate with all servers: we don't block any servers.