This paper introduces Bayesian Flow Networks (BFNs), a new class of
gene...
We consider the problem of generative modeling based on smoothing an unk...
Evolutionary computation is an important component within various fields...
Upside-Down Reinforcement Learning (UDRL) is an approach for solving RL
...
Lately, there has been a resurgence of interest in using supervised lear...
We formally map the problem of sampling from an unknown distribution wit...
Reward-Weighted Regression (RWR) belongs to a family of widely known
ite...
Distribution-based search algorithms are an effective approach for
evolu...
Traditional Reinforcement Learning (RL) algorithms either predict reward...
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge,
p...
This paper proposes a new neural network design for unsupervised learnin...
Many sequential processing tasks require complex nonlinear transition
fu...
Disentangled distributed representations of data are desirable for machi...
Theoretical and empirical evidence indicates that the depth of neural
ne...
There is plenty of theoretical and empirical evidence that depth of neur...
Several variants of the Long Short-Term Memory (LSTM) architecture for
r...
Recently proposed neural network activation functions such as rectified
...
Like a scientist or a playing child, PowerPlay not only learns new skill...