Stanislav Pidhorskyi et al., 2020, arXiv Keyword: Generative, Adversarial learning Problem: AE based approach has poor quality of output distribution.

Hyunjik kim et al., 2019, arXiv Keyword: Bayesian, Process Problem: Underfitting of Neural Process Solution: NP + Self-Attention, Cross-Attention Benefits: Improvement of prediction accuracy, training speed, model capability.

Marta Garnelo et al., 2018, arXiv Keyword: Bayesian, Process Problem: Data inefficiency, hard to train multiple datasets in one.

Marta Garnelo et al., 2018, arXiv Keyword: Bayesian, Process Problem: Weakness of knowledge sharing and data inefficiency of classical supervised learning Solution: Stochastic Process + NN Benefits: Data efficient, prior sharing Contribution: Encapsulation of parameterized NN function family.

Skills Languages : Python : C++ [git+revsic/cpp-obfuscator, git+utilForever/RosettaStone] ML Framework : Tensorflow [git+revsic/tf-glow-tts, git+revsic/tf-diffwave] : PyTorch [git+revsic/torch-nansypp, git+revsic/torch-flow-models] : Jax/Flax [git+revsic/jax-variational-diffwave]