MTL DATA @mtldata

Connecting nodes in the Montreal data community. Since 2014. #AIFest bit.ly/aifest-group Montreal, QC Joined May 2014

Tweets

860
Followers

532
Following

460
Likes

983

CIFAR @CIFAR_News

7 years ago

Thirteen critically important questions will be addressed by the new portfolio of CIFAR research programs: cifar.ca/spring-2019-re… #CIFARPrograms

1 10 25 0 0

View Details

Diagram @diagramventures

7 years ago

Join @breathelifeins and @godialogue on April 4th for the @mtldata meet-up which is all about DataOps.

Breathe Life @breathelifeins

7 years ago

We're co-hosting the next @mtldata meet-up with @godialogue on April 4th and it's all about DataOps! Will you be there? meetup.com/mtldata/events…

0 1 3 0 0

1 4 4 0 0

View Details

My PhD thesis Neural Transfer Learning for Natural Language Processing is now online. It includes a general review of transfer learning in NLP as well as new material that I hope will be useful to some. ruder.io/thesis/

24 556 2K 0 208

View Details

Jeff Dean @JeffDean

7 years ago

Hand-labeling training data for machine learning problems is effective, but very labor and time intensive. This work explores how to use algorithmic labeling systems relying on other sources of knowledge that can provide many more labels but which are noisy.

Google AI @GoogleAI

7 years ago

In collaboration with @Stanford and @BrownUniversity, we present Snorkel Drybell, a variant of the open source Snorkel framework, which explores how existing organizational knowledge can be used as weak supervision to quickly label large training datasets. goo.gl/K2hKxk

5 270 749 0 73

7 174 634 0 54

View Details

WiMLDS Montreal @WiMLDS_Montreal

7 years ago

Excited about #ML and #Fashion ? 👚 Come to our @WiMLDS_Montreal meetup @element_ai on March 8th, to hear @negar_rz talk! Subscribe here: meetup.com/fr-FR/wimlds-m… 😃 #InternationalWomensDay #WiDS2019

4 15 39 0 0

View Details

Ian Goodfellow @goodfellow_ian

7 years ago

I originally thought of GANs as an unsupervised learning algorithm, but so far, to create recognizable object categories, they've needed a supervision signal / labeled images. This new work shows how to get them to work well with few labels.

Mario Lucic @MarioLucic_

7 years ago

How to train SOTA high-fidelity conditional GANs usin 10x fewer labels? Using self-supervision and semi-supervision! Check out our latest work at goo.gl/idWNVs @GoogleAI @ethzurich @TheMarvinRitter @mtschannen @XiaohuaZhai @OlivierBachem @sylvain_gelly

1 66 234 0 26

3 134 481 0 40

View Details

François Chollet @fchollet

7 years ago

The complaints "Python is slow" or "Python is unsafe" seem misguided. The point of Python isn't to be fast or safe, it's to be flexible and hackable, and to interface well with everything else. It has become successful by serving as a frontend from which to call other libraries.

26 279 1K 0 33

View Details

Mario Klingemann💧💦 @quasimondo

7 years ago

Latent Lisa, found in #StyleGAN #FindingMona

13 138 573 0 11

View Details

Ryan Lowe 🥞 @ryan_t_lowe

7 years ago

Last tweet for me on the OpenAI GPT-2 thing, but for those interested I think this video really elevates the discussion. Great work by all parties involved.

Sam Charrington @samcharrington

7 years ago

Really great discussion this eve on @OpenAI's recent language model release and the issues and considerations raised. Thanks @AmandaAskell @AnimaAnandkumar @Miles_Brundage @smerity @WWRob for participating. Those who missed it live can catch the replay at youtube.com/watch?v=LWDbAo…

3 33 91 0 4

0 7 24 0 0

View Details

Jascha Sohl-Dickstein @jaschasd

7 years ago

Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent arxiv.org/abs/1902.06720 <--- this should blow your mind a bit!! Also holds for convolutional networks, batch norm, ... Also, closed form for test predictions resulting from gradient descent training.

5 152 488 0 54

View Details

Jeremy Howard @jeremyphoward

7 years ago

This is literally the first time I've seen am NLP researcher say they want to focus on helping normal people solve normal problems. Hopefully the first of many :)

Lana Teplitsky @STeplitsky

7 years ago

Fascinating presentation by @yoavgo who is focusing his research on what people want: Turning text into structured data. “Information Extraction can be transformative to science” Excel for #NLP. #NaturalLanguageProcessing #AI @allen_ai BIU's NLP lab u.cs.biu.ac.il/~nlp/

3 51 286 0 26

4 77 409 0 26

View Details

hardmaru @hardmaru

7 years ago

“As someone who is deeply interested in AGI, I find ImageNet much less interesting now, precisely because it can be solved with models that have little global understanding of images.”

Eric Jang @ericjang11

7 years ago

There is the neat and counterintuitive BagNet paper that is making the rounds on #ML Twitter. Here are my (quick) thoughts on it: blog.evjang.com/2019/02/bagnet…

6 43 173 0 21

4 22 127 0 13

View Details

Kerem Turgutlu @KeremTurgutlu

7 years ago

medium.com/@keremturgutlu… Here, I tried to explain building blocks of SOTA ULMFIT model. What is an AWD-LSTM? How Dropout is used everywhere? What is a QRNN and why might it be better? ...I also used excel spreadsheets to simplify things in a different way :)

2 61 245 0 41

View Details

Gilles Louppe @glouppe

7 years ago

TIL when preparing my second deep learning lecture that the operators' manual for Rosenblatt's Mark 1 Perceptron machine was a classified document. It became unclassified only in 1977. The manual can now be found at apps.dtic.mil/dtic/tr/fullte…

0 19 61 0 2

View Details

Thomas Wolf @Thom_Wolf

7 years ago

.@kaushal316 wrote a nice step-by-step tutorial on how to finetune BERT on a classification task (@kaggle Toxic Challenge) Covers everything from data processing to model modification Results are top-10% w. a very simple 30-lines-of-code single model 👇 medium.com/huggingface/mu…

1 101 354 0 63

View Details

Jeremy Howard @jeremyphoward

7 years ago

Such an inspiration: @alexandrecadrin is both a radiologist, and a kaggle-winning deep learning expert. He is the only one in the world so far - but there will be more to come! Thank you @bhutanisanyam1 for helping to tell his amazing story. hackernoon.com/interview-with…

5 42 193 0 12

View Details

Pieter Abbeel @pabbeel

7 years ago

This Fri 2/8 is deadline to apply to fullstackdeeplearning.com taking place March 2-3 in Berkeley. Also: @l2k from Weights & Biases / FigureEight and @jeremyphoward from fast.ai joined our guest speakers @RichardSocher (Salesforce) & Raquel Urtasun (Uber/Toronto).