Browsing: Yannic Kilcher
FixMatch is a simple, yet surprisingly effective approach to semi-supervised learning. It combines two previous methods in a clever way…
Offline Reinforcement Learning has come more and more into focus recently in domains where classic on-policy RL algorithms are infeasible…
A closer look at the OpenAI microscope, a database of visualizations of the inner workings of ImageNet classifiers, along with…
This paper establishes a framework for looking at out-of-distribution generalization failures of modern deep learning as the models learning false…
Geoffrey Hinton and his co-authors describe a biologically plausible variant of backpropagation and report evidence that such an algorithm might…
The Longformer extends the Transformer by introducing sliding window attention and sparse global attention. This allows for the processing of…
Multi-Task Learning can be very challenging when gradients of different tasks are of severely different magnitudes or point into conflicting…
This casting of our field in terms of ideological narrow-sighted group-think is disgusting. Keep Science about ideas! Links: YouTube: Twitter:…
Classic RL “stops” the world whenever the Agent computes a new action. This paper considers a more realistic scenario where…
The cross-entropy loss has been the default in deep learning for the last few years for supervised learning. This paper…