Ahsan Alvi

PhD student in machine learning @UniOfOxford.

[Ivan Kiskin 🇺🇦 @IvanKiskin1]

Interested in watching the mean paper review scores rise while reviewers ignore your rebuttals for NeurIPS Dataset and Benchmarks? Check out this colab which connects to OpenReview's API:

https://t.co/S7m0ExfHSX
Highlights:

Mean before rebuttal: 5.5
Mean after rebuttals: 5.8

[Robin Hood @robinhood]

Lovely to have all these new followers .. can we just check that you know that you’re following The World Wide Robin Hood Society in Nottingham and not the Robin Hood App .. if so .. a big welcome from Sherwood 🙌

[Adam Cobb @Adam_D_Cobb]

New work on applying HMC to BNNs! Our symmetric splitting approach preserves the entire Hamiltonian and can be run on a single GPU.

All the code is in hamiltorch :)

Paper: https://t.co/88vMH1HzPb
Blog post: https://t.co/TjIc2gHkYn

Work with @BJalaian!

[Adam Cobb @Adam_D_Cobb]

Looking forward to the ICML Uncertainty and Robustness in Deep Learning Workshop. @mpvadera and I will be available at the poster session to discuss our benchmarking toolbox "URSA". This is work with @BJalaian and Ben Marlin (UMass).
https://t.co/7PMqV55ho7

[Ed Wagstaff @EdWagstaff]

We have two functions f and g. For any ε>0, some δ>0 satisfies ||g(x) - g(y)|| < δ => ||f(x) - f(y)|| < ε. Does this property have a name? d(x, y) := ||g(x)-g(y)|| is a pseudometric. Is "f is continuous wrt this pseudometric" the best way to say this? (NB g may not be invertible)

[Adam Cobb @Adam_D_Cobb]

Have updated website to include recent work. Includes NeurIPS BDL workshop paper on HMC and Robin's (Bin Xin Ru) ICLR paper on BayesOpt. #bdl2019 #ICLR2020
https://t.co/XMAMccwB3w

[Ahsan Alvi @ahsalvi]

https://t.co/phf19dwNPC

[Ahsan Alvi @ahsalvi]

https://t.co/nXjv0HaQYi

[Ahsan Alvi @ahsalvi]

That's awkward....
"Production of Brexit 50p coin paused amid exit uncertainty" https://t.co/tGHqWQJbZz

[Massimo @Rainmaker1973]

Recalling and explaining the popular internet phenomenon of "The Dress" with the help of some graphical tools https://t.co/lF7BunC77b [source of the gif: https://t.co/SkYkQDwYqH]

[AWS Startups @AWSstartups]

Using machine learning & quantum physics, @GTN_LTD is overcoming challenges in drug discovery: https://t.co/bWzbhaAOZt

[Roger Grosse @RogerGrosse]

In ML, it's often simultaneously the case that (1) the announcement of a research result is accurate, informative, and measured, and (2) most of the excitement is from people misinterpreting the result as more profound than it really is.

[Dana Randall @DataRandAlgs]

Only at a math conference do you hear phrases like, "In a randomly mating population..."

[Sophia Armen @SophiaArmen]

all I see is hummus

[Ahsan Alvi @ahsalvi]

"My analysis suggests that researchers are abandoning TensorFlow and flocking to PyTorch in droves."
Was TF 2.0 too late?

https://t.co/jBtj72AOHY

[Adam Cobb @Adam_D_Cobb]

hamiltorch

A PyTorch-based library for Riemannian Manifold Hamiltonian Monte Carlo (RMHMC).

Work with @atilimgunes in a Python package that can perform HMC over neural networks.

Blog post: https://t.co/QZIseOGwuU
Repo: https://t.co/Ok2rg688A7
Paper: https://t.co/ZOGHcVrZcy

[Mark Riedl @mark_riedl]

Today’s realities:

1. Non-neural net code written more than 5 years ago works just fine

2. Neural net code written a year ago on TensorFlow doesn’t work anymore

[Marcus Borba @marcusborba]

A global team of scientists have developed an #AI system to detect 17 diseases from exhaled breath with 86% accuracy
by @spelldotrun
#artificialintelligence #machinelearning #datascience #bigdata #analytics #deeplearning #ml #medicine #health #healthcare