Statistical Learning
bc8f76d9caadd48f77025b1c889d2e2d-Supplemental-Conference.pdf
Table 1 summarises various approaches for learning to defer.
A Unified View of cGANs with and without Classifiers
Conditional Generative Adversarial Networks (cGANs) are implicit generative models which allow to sample from class-conditional distributions.
Training stochastic stabilized supralinear networks by dynamics-neutral growth
However, these models were not capable of actually achieving the brain's performance on its wide range of complex computations.
A Gaussian Process-Bayesian Bernoulli Mixture Model for Multi-Label Active Learning
Multi-label classification (MLC) allows complex dependencies among labels, making it more suitable to model many real-world problems. However, data annotation for training MLC models becomes much more labor-intensive due to the correlated (hence non-exclusive) labels and a potentially large and sparse label space.
Instance-Conditioned GAN
Finally, we extend IC-GAN to the class-conditional case and show semantically controllable generation and competitive quantitative results on ImageNet; while improving over BigGAN on ImageNet-L T. Code and trained models to reproduce the reported results are
Efficiently Identifying Task Groupings for Multi-Task Learning Christopher Fifty
Multi-task learning can leverage information learned by one task to benefit the training of other tasks. Despite this capacity, naïvely training all tasks together in one model often degrades performance, and exhaustively searching through combinations of task groupings can be prohibitively expensive.