xiaoxiong

working on speech processing and deep learning.

[xiaoxiong @xiaoxiong]

@AGItechgonewild @bindureddy Isn’t cup 5 the correct answer?

[Everett Public Schools.WA @EverettSchools]

CORRECTION: The student is quarantined and the few students who were in contact, along with family members, are quarantined and will be tested if they develop symptoms.

[Google DeepMind @GoogleDeepMind]

Spectral methods underpin many classic machine learning algorithms and much of scientific computing. Today we are open sourcing the code for Spectral Inference Networks, our ICLR paper on how to apply spectral methods in large domains using deep learning: https://t.co/Svid74zMLc

[JASA @ASA_JASA]

This Room Acoustics Modeling and Auralization paper provides benchmarks that can be used to assess the performance of broadband techniques in a relatively straightforward configuration with precisely specified boundary conditions. https://t.co/yE9O8rVwvy @DukeEngineering

[Google DeepMind @GoogleDeepMind]

Our new paper, “Reinforcement Learning, Fast and Slow”, reviews recent techniques in deep RL that narrow the gap in learning speed between humans and agents, & demonstrate an interplay between fast and slow learning w/ parallels in animal/human cognition:

https://t.co/Cc3uzH1iMp

[Thang Luong @lmthang]

Introducing UDA, our new work on "Unsupervised data augmentation" for semi-supervised learning (SSL) with Qizhe Xie, Zihang Dai, Eduard Hovy, & @quocleix. SOTA results on IMDB (with just 20 labeled examples!), SSL Cifar10 & SVHN (30% error reduction)! https://t.co/Uoj2Rb7Etx

[JASA @ASA_JASA]

How to measure community tolerance levels for noise: https://t.co/QjVCTJpJaJ #INAD2019 @NTNU

[Speech Graphics @speechgraphics]

Congratulations to @UCSF for their incredible breakthrough work on a brain-to-machine interface manipulating brain signals into speech! We are proud to help with the visualisation of this powerful new voice!
https://t.co/W5tehLgrWl

[Daniel Sinclair @_DanielSinclair]

Here's a video of a Chimpanzee using Instagram. It's eye-opening. https://t.co/FEfIgQSGa6

[xiaoxiong @xiaoxiong]

@Prof_hrk @hidekikawahara AI神学-> ?

[Matt Henderson @matthen2]

.@poly_ai has just released a collection of datasets for conversational AI, consisting of hundreds of millions of examples- https://t.co/kZdk7ZtZhu

[Pieter Abbeel @pabbeel]

Very excited to announce a project 3 years in the making: BLUE, a low-cost, safe, capable robot designed from the ground up with AI in mind.

Want BLUE? You can now sign up for priority access here: https://t.co/bdK7ouRABK

Learn more here: https://t.co/vB0i39aHTE

w/@Cthephen

[TechCrunch @TechCrunch]

Slack integration with Office 365 one more step toward total enterprise integration https://t.co/5GpffIHlnc by @ron_miller

[TechCrunch @TechCrunch]

Zoom's road to an IPO hasn't been without hiccups https://t.co/UBZKkQz8aD

[Ian Goodfellow @goodfellow_ian]

An exciting property of style-based generators is that they have learned to do 3D viewpoint rotations around objects like cars. These kinds of meaningful latent interpolations show that the model has learned about the structure of the world. https://t.co/7YH7GCOkaL

[Scott Hanselman 🌮 @shanselman]

Anytime I’m traveling I use Google Translate to check translations in real time on signage. You have to see it to believe it. This is real and LIVE while you move your camera. @ Paris

[xiaoxiong @xiaoxiong]

@Uber_SING I didn't get the place to enter the POOLFRIDAY code before choosing uberX. Do you mean you will refund me 23$ for my trip?

[xiaoxiong @xiaoxiong]

@Uber_SING It's [email protected].

[xiaoxiong @xiaoxiong]

@Uber_SING I just got a 28+$ fare from NTU to Fusionopolis. I entered POOLFRIDAY and the Uber software recognized it. Can you explain?

[xiaoxiong @xiaoxiong]

@Uber_SING How come my fare is 20+SGD even after I entered POOLFRIDAY?