Towards a Human-like Open-Domain Chatbot (Google Research/Brain Team) https://t.co/rbtjVVddQU
— /MachineLearning (@slashML) January 28, 2020
Towards a Human-like Open-Domain Chatbot (Google Research/Brain Team) https://t.co/rbtjVVddQU
— /MachineLearning (@slashML) January 28, 2020
Even my continued fiddling with the SHA-RNN model shows there's a _lot_ to be studied and explored. I haven't published new incremental progress but you can tie the RNN across the 4 layers to substantially decrease total params yet get nearly equivalent perplexity results.
— Smerity (@Smerity) January 28, 2020
Open-domain conversation is an extremely difficult task for ML systems. Meena is a research effort at @GoogleAI in this area. It's challenging, but we are making progress towards more fluent and sensible conversations.
— Jeff Dean (@JeffDean) January 28, 2020
Nice work, Daniel, @lmthang & everyone involved! https://t.co/nqpsBKlpkl pic.twitter.com/vjkXoSUHf3
The other dimension here is monolingual vs multilingual models. I think monolingual models in low-resource languages currently have an edge e.g. as seen in our MultiFiT paper.
— Sebastian Ruder (@seb_ruder) January 28, 2020
Procedural Content Generation via Reinforcement Learning
— hardmaru (@hardmaru) January 28, 2020
“A new approach to procedural content generation in games, where level design is framed as a game (as a sequential task problem), and the content generator itself is learned.”https://t.co/Inj66Hn8pD pic.twitter.com/2B6P6tlh9d
A lot has been said about the dangers of large-scale language model trained on the internet, like GPT-2.
— Mark O. Riedl (@mark_riedl) January 27, 2020
We fine-tuned a version of GPT-2 to avoid generating descriptions of non-normative behavior (killing, suicide, things inconsistent with social norms) https://t.co/V12NM8HSc7 pic.twitter.com/5GCMtjnEM6
Clean TF2 Implementation of "An end-to-end deep learning architecture for graph classification" (M. Zhang et al., 2018) https://t.co/a7M9lgtcpW
— /MachineLearning (@slashML) January 26, 2020
ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network
— roadrunner01 (@ak92501) January 23, 2020
pdf: https://t.co/QqIUyRJSpV
abs: https://t.co/olyFFQe4tT pic.twitter.com/RvrpGsZb8s
Survey of machine-learning experimental methods at #NeurIPS2019 and #ICLR2020 https://t.co/kDexrfjv79
— Gael Varoquaux (@GaelVaroquaux) January 22, 2020
Results of a poll @bouthilx and I ran, with some analysis and discussion of statistical power and reproducibility. pic.twitter.com/FhebPSOCRW
The quiet semisupervised revolution continues https://t.co/FAY4v9aHbe
— Ian Goodfellow (@goodfellow_ian) January 22, 2020
Code is up: https://t.co/mYFJdWwJaT
— David Berthelot (@D_Berthelot_ML) January 22, 2020
And being my usual distracted self, I forgot one co-author from the list: @alexey2004 (Sorry Alex!) The code for ImageNet will come later.
This is a very interesting paper. It shows that a tweaked ResNet50 is about as accurate as EfficientNet-B4 but >3x faster.
— Jeremy Howard (@jeremyphoward) January 21, 2020
The EfficientNet paper measured FLOPS, which is a theoretical performance measure, rather than time, which is what actually matters.https://t.co/Hzyokmf2x7 pic.twitter.com/cyBiueqPuf