dls-2021 | Deep Learning JP - Part 9

Generalized Zero-Shot Learning via Disentangled Representation

Towards Transparent and Explainable Attention Models

Sharpness-Aware Minimization for Efficiently Improving Generalization

Scaling Laws for Neural Language Models

Learning to combine top down and bottom-up signals in recurrent neural networks with attention over modules

Toward Fast and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis

https://www2.slideshare.net/DeepLearningJP2016/dltoward-fast-and-stabilized-gan-train more

MEMORY OPTIMIZATION FOR DEEP NETWORKS (ICLR’21)

wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations (NeurIPS, 2020)

AutoDropout: Learning Dropout Patterns to Regularize Deep Networks

深層強化学習はなぜ難しいのか？Why Deep RL fails? A brief survey of recent works.