Mehryar E.

Quantitative Researcher at @MesirowFin I tweet about #Machine_learning #NLP #Computer_vision #Time_Series #FX #Quant Views are my own. RT are not endorsements.

[Brady Neal @CasualBrady]

@ChristophMolnar https://t.co/1dRV4l5eM0 :)

[TensorFlow @TensorFlow]

🖥️ Convert a Python model to run in the web browser via TensorFlow.js!

Reach a wider audience with the simplicity and scale of the web. Share a web page and have people try your model in seconds - no complex environment setup required

Take the codelab → https://t.co/KFx3JEsLa5

[Saeed @saeedamenfx]

Read all the #QuantLinkADay quant papers which I've posted over the past year! https://t.co/Z8MCoQdCrS

[Xiaolong Wang @xiaolonw]

New work with Yinbo Chen, one of my first PhD students: Learning Continuous Image Representation
with Local Implicit Image Function. Check our video showing images in arbitrary resolutions.

proj: https://t.co/5GHK1URPdA
code: https://t.co/x20Q1NzX3Q

@YinboChen @SifeiL
(1/n)

[best_pyfinance @BPyfinance]

#4 🔥 repos: kylejusticemagnuson/pyti, Python library of various financial technical indicators, https://t.co/9fY005nsMK , Forks: 136, Stars: 446 #PythonFinance, #quantfinance

[Michael Bronstein @mmbronstein]

Can we use #graphneuralnetworks when the graph is not given? In a new blog post I show that a new type of "latent graph learning" architectures can be thought of as a modern take on #manifoldlearning

https://t.co/p40Sod9EOr

[Alfredo Canziani @ ICML @alfcnz]

Week ⑬ videos 🎥 are up! 🎉

Lecture: https://t.co/6t46aOxjjy
Practicum: https://t.co/45EN5FDX52
Transcript: https://t.co/Sz3EhQ83Nf

Learn about:
• conv on graph as template matching;
• … using spectral 👻 theorem;
• (an)isotropic GCNs;
• implementing gated GCNs.

[Amit Chaudhary @amitness]

Amazing article from @eugeneyan describing developments in NLP from RNNs(1985) to Big Bird(2020).

Really helps get a bird's-eye view of this rapidly progressing field.

https://t.co/ZOgjinhHwb

[Adam W. Harley @AdamWHarley]

After five years of procrastinating on this, I finally released a clean repo for my interactive 2d/3d #visualization of #NeuralNetworks: https://t.co/cEOcTfSwK8

[Denny Britz @dennybritz]

Just finished a trip down memory lane. Deep Learning's Most Important Ideas - A Brief Historical Review: https://t.co/XpBxi9xrCF

If you want to get into Deep Learning research, these are what I consider the most important papers to start with!

[Mehryar E. @MEmambakhsh]

Where Is Robotics Heading? Perspectives From iRobot (Colin Angle), Stanley Black & Decker, And Robots... via @forbes https://t.co/0RyHQPRBeu

[Michael Bronstein @mmbronstein]

Do we need deep graph neural networks? In a new blog post @TDataScience I try to find out https://t.co/8J0q0BJ565 #geometricdeeplearning #graphneuralnetworks

[Tomasz Malisiewicz @quantombone]

Implicit Mesh Reconstruction from Unannotated Image Collections. Nice 3D recovery with a clever parameterization of shape. https://t.co/DO162A0aow #robotics #computervision

[Mike Tamir, PhD @MikeTamir]

“Time Series Forecasting Best Practices & Examples” https://t.co/LrC4zkzx7e #AI #DeepLearning #MachinLearning #DataScience

[AK @_akhaliq]

COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder
pdf: https://t.co/YIgRbU4R1X
project page: https://t.co/rLRookjwcU
video: https://t.co/oV2r5I9z9P

[Mehryar E. @MEmambakhsh]

The Frameworks that Google, DeepMind, Microsoft and Uber Use to Train Deep Learning Models at Scale https://t.co/VFmcR9i7Hf

[Mehryar E. @MEmambakhsh]

"The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch."

https://t.co/ZS9yZEpOQo

[Arno Solin @arnosolin]

Fresh from the press: "Applied Stochastic Differential Equations" with @simosarkka and published by @CambridgeUP.
Physical books: https://t.co/0tUTyiwQq9
Online PDF version: https://t.co/FumlgSdsMs
Codes: https://t.co/yL00iNAaDY

[Towards Data Science @TDataScience]

Sktime: a Unified Python Library for Time Series Machine Learning by Alexandra Amidon https://t.co/I5MKIWBn3c

[Mehryar E. @MEmambakhsh]

Deep Reinforcement Learning and
its Neuroscientific Implications

https://t.co/GbdgxKgs50