considerahead's profile picture. Senior Deep Learning Research Scientist at @3M Dublin. Engineer with a passion for robotics.  I work on 3D mesh Transformers.  All views are mine

Francis Yates

@considerahead

Senior Deep Learning Research Scientist at @3M Dublin. Engineer with a passion for robotics. I work on 3D mesh Transformers. All views are mine

Francis Yates reposted

Most of these signatories have a distorted view of what is coming next with AI. The distortion is due to their inexperience, naïveté on how difficult the next steps in AI will be, wild overestimates of their employer's lead and their ability to make fast progress, and financial…


Francis Yates reposted

I try my best to not talk about Irish politics, but getting sent things like this by my Garda friends just angers me too much. This happened today. The police (Gardai) in Ireland have been attacked and bullied by scumbags for years now. They know they can get away with it.…


Francis Yates reposted

Emergent in-context learning with Transformers is exciting! But what is necessary to make neural nets implement general-purpose in-context learning? 2^14 tasks, a large model + memory, and initial memorization to aid generalization. Full paper arxiv.org/abs/2212.04458 🧵👇(1/9)

LouisKirschAI's tweet image. Emergent in-context learning with Transformers is exciting! But what is necessary to make neural nets implement general-purpose in-context learning? 2^14  tasks, a large model + memory, and initial memorization to aid generalization.

Full paper arxiv.org/abs/2212.04458

🧵👇(1/9)

Next week I'm going to be joining @3M as a Senior Research Scientist for AI in dental applications. Can't wait, sad to be leaving @VisualAIPeople after 4 great years.


Francis Yates reposted

One difference between experienced ML researchers with those new to the field is the amount of visualization that one does including visualizing training data, augmentations, parameters, gradients, predictions, etc. A codebase with only end metric plots almost always means bugs.


Francis Yates reposted

Looks to me like stage 2) argument:

AGI skepticism comes in three stages: 1) It’s completely impossible. 2) It’s possible, but it would be prohibitively expensive to be useful 3) I said it was a good idea all along. Imgs by Dall-e

woj_zaremba's tweet image. AGI skepticism comes in three stages: 
1) It’s completely impossible. 
2) It’s possible, but it would be prohibitively expensive to be useful
3) I said it was a good idea all along.

Imgs by Dall-e
woj_zaremba's tweet image. AGI skepticism comes in three stages: 
1) It’s completely impossible. 
2) It’s possible, but it would be prohibitively expensive to be useful
3) I said it was a good idea all along.

Imgs by Dall-e


This is unbelievably based

Academics: We value research quality more than quantity. Also academics: Look! Come check out our 100+ papers at top conference!



Has anyone got any advice/links on optimizing v,v large (2gb+) TF vision models? - for inference/training


Francis Yates reposted

What's the differences among ... Latent space, feature space, embedding space, representation space, latent feature, feature embedding, latent representation, embedding representation, latent embedding, and feature representation? 🤔


Francis Yates reposted

AI isn’t “hijacking” art history, it is providing the tools it needs to scale! The first automobile was not faster than a horse and carriage, but it had the attributes that allow it to scale.

Academics: We value research quality more than quantity. Also academics: Look! Come check out our 100+ papers at top conference!



Francis Yates reposted

#COP26 has just begun while I started working in the renewable industry today. As a welcome gift, I'd really appreciate if all the world leaders agreed to dump 30 years of work on my desk.


Big fan of @ramin_m_h talk on the paper 'Liquid Neural Netwoks' about a 'new class of time-continuous recurrent neural network models'. Really good visualisation. youtube.com/watch?v=IlliqY…

considerahead's tweet card. Liquid Neural Networks

youtube.com

YouTube

Liquid Neural Networks


Francis Yates reposted

Does my GAN's loss go down every day? No. But does it try its hardest to make its image quality go up over time? Also no


The ability to wrap arbitrary python/NumPy operations within a Tensorflow graph - and save - then serve it, is a massively underrated benefit of Tensorflow. Main changes include changing from python lists to TensorArrays.


Francis Yates reposted

So many exciting new frontiers in ML, it's hard to give a short list, particularly in new application areas (e.g. in the physical and biological sciences). But the Big Question is: "How could machines learn as efficiently as humans and animals?" This requires new paradigms.

i want to get into ML research, what topic would you recommend? nothing. now it is not time to get into ML research. now its time to either observe what others are doing, or to build innovative applications using established techniques, or both.



Francis Yates reposted

We do not have an answer to that question, and the gap to bridge is enormous (how can people learn to drive a car in 20h of practice?) Decisive advances towards an answer will mark a new era in AI. That's why I work on self-supervised learning. It's our best shot at the moment.


Francis Yates reposted

those who attack space maybe don’t realize that space represents hope for so many people


Francis Yates reposted

The conversations around Falcon and the Winter Soldier being “too political” when it’s just detailing Black people’s existence in the US shows us that the “no politics at work” policies will reprimand Black people for just sharing our experiences & existence


Francis Yates reposted

New preprint: "Impact Invariant Control with Applications to Bipedal Locomotion," by William Yang. During impacts, robots undergo large and rapid changes in velocity. State estimation, and thus control, in these periods are incredibly difficult. (1/2) arxiv.org/abs/2103.06907

MichaelAPosa's tweet image. New preprint: "Impact Invariant Control with Applications to Bipedal Locomotion," by William Yang. 

During impacts, robots undergo large and rapid changes in velocity. State estimation, and thus control, in these periods are incredibly difficult. (1/2)

arxiv.org/abs/2103.06907

Loading...

Something went wrong.


Something went wrong.