Suggested papers

Here’s a list of papers that may be worth discussing at upcoming meetings sorted by general topics.

Convolutional Neural Networks (CNNs)

• Attention Augmented Convolutional Networks

Generative Adverserial Networks (GANs)

• Generalization and Equilibrium in Generative Adversarial Nets (GANs)
• GauGAN: Semantic Image Synthesis with Spatially-Adaptive Normalization + blog post
• Deblending galaxy superpositions with branched generative adversarial networks
• GAN Dissection: Visualizing and Understanding Generative Adversarial Networks + blog post
• 3D convolutional GAN for fast simulation

Recurrent Neural Networks (RNN)

• Recurrent Attentive Neural Process for Sequential Data

Out-of-Distribution Detection

• Likelihood Ratios for Out-of-Distribution Detection
• Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network
• Normalizing flows for deep anomaly detection

Other

• WaveGlow: A Flow-based Generative Network for Speech Synthesis
• Training behavior of deep neural network in frequency domain
• Backward Feature Correction: How Deep Learning Performs Deep Learning
• Up to two billion times acceleration of scientific simulations with deep neural architecture search