Variational auto-encoders are powerful probabilistic models in generativ...
Evolution of beliefs of a society are a product of interactions between
...
The goal of explainable Artificial Intelligence (XAI) is to generate
hum...
Deep Gaussian Process as a Bayesian learning model is promising because ...
Optimal transport (OT) formalizes the problem of finding an optimal coup...
It is desirable to combine the expressive power of deep learning with
Ga...
Adversarial images highlight how vulnerable modern image classifiers are...
Limited expert time is a key bottleneck in medical imaging. Due to advan...
Neural network architectures are achieving superhuman performance on an
...
Obtaining solutions to Optimal Transportation (OT) problems is typically...
We consider constrained policy optimization in Reinforcement Learning, w...
We present a novel interactive learning protocol that enables training
r...
State-of-the-art deep-learning systems use decision rules that are
chall...
Cooperation is often implicitly assumed when learning from other agents....
For many problems, relevant data are plentiful but explicit knowledge is...
We consider the problem of manifold learning. Extending existing approac...
Cooperative communication plays a central role in theories of human
cogn...
We propose interpretable deep Gaussian Processes (GPs) that combine the
...
Cooperation information sharing is important to theories of human learni...
We propose a Standing Wave Decomposition (SWD) approximation to Gaussian...
Machines, not humans, are the world's dominant knowledge accumulators bu...
There is a widespread need for statistical methods that can analyze
high...