David Fagan

3 day week evangelist :D Sometimes I have good ideas (patent pending)

[Boring Brothers @boringkearney]

Awesome day with uncle Joe, we stopped off for a chicken fillet roll in Fundalk had a miwadi in a public house, had an in depth discussion about the weather and reminisced about the time I single handidly beat the Black and Tans out of Ireland #JoeBiden

[Boring Brothers @boringkearney]

Gave uncle Joe a lend of my Wolfe tones CD for the trip home #JoeBiden

[Jean de Dieu Nyandwi @Jeande_d]

Introduction to Deep Learning, Carnegie Mellon 2022-23

A nice set of lectures that covers the foundation of deep learning. Goes all the way from the history of DL, neural network theories, techniques & algorithms that are used in present times.

Lectures: https://t.co/0DVUK43FpS

[Chris Kamara @chris_kammy]

Ok so you make one mistake 13 years ago & no one will let you forget it 🤷🏽‍♂️ 😂🤣😂🤣

[ian bremmer @ianbremmer]

one of the most informative maps you'll see

the ‘true size’ of countries when not distorted on a sphere

[David Fagan @dvpfagan]

So I was part of the Red Team. Great learning experience and a win to boot.

[Trūata @TruataPrivacy]

📢 We are delighted to share the news that Trūata has been awarded first place in the PETs Prize Red Team Challenge: Advancing Privacy-Preserving Federated Learning!

Visit https://t.co/qOOUmcf5se for more details.

#PETs #SummitForDemocracy #Privacy #FederatedLearning

[Chris Bakke @ChrisJBakke]

GPT-5: can perfectly build any website

GPT-6: can build and run a company

GPT-7: passes Turing test

GPT-8: overthrows world governments

GPT-9: fails to understand how Jira is supposed to work, gives up, asks humans for help

[Jason H. Moore, PhD @moorejh]

Gordon E. Moore, Intel Co-Founder Behind Moore’s Law, Dies at 94 https://t.co/mVII8xZ6uf #retrocomputing #RIP

[Gary Marcus @GaryMarcus]

Speaking of bullshit, anyone remember this?

[Tom Nash @iamtomnash]

the unluckiest man alive

[David Fagan @dvpfagan]

Fair play to him, not sure I’d have the balls to do it if I suffered with one.

[SPORTbible @sportbible]

Watford’s Ken Sema suffers with a stutter, but he bravely came out and did the post-match interview last night... ❤️

This will really help a lot of people. Anyone who suffers with a stammer knows how hard and deflating it can be. Brilliant @Semaken! 👏

[Skiplagged | Travel Hacks ✈️ @Skiplagged]

Fog waves through the Bay Area 🌁

🎥 Fredrick D. Barnes

#California

[David Fagan @dvpfagan]

Do you remember when you joined Twitter? I do! #MyTwitterAnniversary

[Massimo @Rainmaker1973]

How a book written in 1910 could teach you calculus better than several books of today

[Calculus Made Easy, by Silvanus P. Thompson, 1910 - full text pdf: https://t.co/W4gspJGhHK or with the table of contents: https://t.co/55dkZzX4XV]

[David Fagan @dvpfagan]

I knew there was a reason I didn't go to the gym :D

[World of Statistics @stats_feed]

The average gym dumbbell has 362 times more bacteria than a toilet seat.

[Sebastian Raschka @rasbt]

There will be a full-day workshop on deep learning for tabular data at #NeurIPS2022 this year! 🙌

To prepare for the panel, I also just found 4 new papers to review; will add to the list below 📚!
It'll be fun!

(the event is on Dec 2, 2022; more info: https://t.co/OY35qVQAKg)

[Sebastian Raschka @rasbt]

A Short Chronology Of Deep Learning For Tabular Data:
https://t.co/VAXJRBMyzj

Deep tabular methods are an interesting research direction! So, this morning, I sat down and summarized my thoughts + the recent papers I read.

[Jason H. Moore, PhD @moorejh]

The Modern Mathematics of Deep Learning https://t.co/3Yme0GM0Ve #deeplearning #mathematics HT @KirkDBorne

[Linus @thesephist]

NEW DEMO!

Exploring the "length" dimension in the latent space of a language model ✨

By scrubbing up/down across the text, I'm moving this sentence up and down a direction in the embedding space corresponding to text length — producing summaries w/ precise length control (1/n)

[Sebastian Raschka @rasbt]

This week's update to the tabular list features (surprise, surprise)
💫diffusion models💫!

"TabDDPM: Modeling Tabular Data with Diffusion Models" https://t.co/ghg553JOCy

Why is this useful & interesting?
1) Imbalanced data and oversampling;
2) Privacy.

How it works?
👇 1/13