Stochastic RNNs without Teacher-Forcing

Channel:
Switzerland Yannic Kilcher
Subscribers:
294,000
Published on ● Video Link: https://www.youtube.com/watch?v=_PyusGsbBPY


Duration: 18:19
3,039 views
60

We present a stochastic non-autoregressive RNN that does not require teacher-forcing for training. The content is based on our 2018 NeurIPS paper:

Deep State Space Models for Unconditional Word Generation
https://arxiv.org/abs/1806.04550



Other Videos By Yannic Kilcher


2019-05-10Reinforcement Learning, Fast and Slow
2019-05-09S.H.E. - Search. Human. Equalizer.
2019-05-06Blockwise Parallel Decoding for Deep Autoregressive Models
2019-04-27Discriminating Systems - Gender, Race, and Power in AI
2019-02-19The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
2019-02-18Neural Ordinary Differential Equations
2019-02-18GPT-2: Language Models are Unsupervised Multitask Learners
2019-02-02Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
2019-01-30BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2019-01-09What’s in a name? The need to nip NIPS
2018-12-21Stochastic RNNs without Teacher-Forcing
2018-12-18Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
2018-04-07World Models
2018-03-18Curiosity-driven Exploration by Self-supervised Prediction
2017-12-13git for research basics: fundamentals, commits, branches, merging
2017-11-28Attention Is All You Need
2017-08-28Reinforcement Learning with Unsupervised Auxiliary Tasks
2017-08-09Learning model-based planning from scratch
2017-08-04Imagination-Augmented Agents for Deep Reinforcement Learning


Tags:
NeurIPS2018
NIPS2018
NLP
deep learning
RNN