Machine Intelligence Group @ Edinburgh @machine_group X Profile

Machine Intelligence Group @ Edinburgh

@machine_group

Followers

202

Following

11

Media

2

Statuses

36

The Machine Intelligence Research Group @ University of Edinburgh, led by Timothy Hospedales

https://t.co/Qh1M0wqsp4

Edinburgh, Scotland

Joined June 2019

Don't wanna be here? Send us removal request.

Machine Intelligence Group @ Edinburgh

@machine_group

6 years

Check out the new meta-learning survey from @tmh31, @_AntreasAntonio, Paul Micaelli, and @AmosStorkey!

Antreas Antoniou

@AntreasAntonio

6 years

Hello everyone, Are you a meta-learning researcher wanting to quickly catch up on the latest developments across the board? Or perhaps a newcomer that doesn’t know where to start? Well, we have written a survey paper just for you. Paper:

0

2

Henry Gouk

@henrygouk

3 years

Inspired by all the data and compute hungry advances recently, we're hosting a workshop on Affordable #MachineLearning at @InfAtEd on June 30th. Come along for a mix of invited talks, posters (submit one!), and more. Details here: https://t.co/8Te9dcBw4S

1

4

28

Henry Gouk

@henrygouk

3 years

The panel discussion for our #ICLR2023 workshop on Domain Generalisation starts in 45 minutes! Join us to hear what some leading researchers (@zacharylipton, @BoqingGo, @QiDou_, etc) looking at robustness to distribution shift think about what we need. https://t.co/XwPs8xzehv

1

2

11

Henry Gouk

@henrygouk

3 years

Hello, everyone! We will be organizing an online workshop at ICLR 2023 aimed at one question: What do we need for successful domain generalization? The workshop will include invited talks from David Lopez-Paz, @AmosStorkey, @tommasi_tatiana, and @ylqzd2011 1/2

2

9

36

Wei-Hong Li

@WayHomeLi

3 years

We are organizing the Universal Representations for Computer Vision Workshop at #BMVC2022 on Nov. 24th in London. We have a fantastic set of speakers! https://t.co/WBn1dy8qc5… We invite submissions of regular and short papers (See Call for Paper for more details).

1

7

11

Timothy Hospedales

@tmh31

3 years

My Lab at Samsung AI Research Cambridge is #hiring research scientist and ML research engineer positions. Skilled in meta-learning, neuro-symbolic, foundation models, vision and language, robot learning, on-device learning? Apply online https://t.co/ELTrrMFUKi #MachineLearning

1

28

97

Timothy Hospedales

@tmh31

3 years

Wondering about state of the art in algorithmic fairness and bias in AI? @yongshuozong' benchmark suite evaluates algorithms comprehensively across medical AI tasks. Bias is pervasive and fairness is hard to find. Paper & Code: https://t.co/rkRZXc4vQ9

1

5

13

Henry Gouk

@henrygouk

3 years

Happy to announce that I've been awarded a #RAEngResearch Fellowship for 2022! Over the next 5 years I'll be working on making machine learning reliable for problems with very little data. Thanks to @InfAtEd @EdinburghUni @tmh31 for the support!

Royal Academy of Engineering

@RAEngNews

3 years

We are delighted to reveal the 17 new awardees receiving a #RAEngResearch Fellowship for 2022. Deep water mooring lines for floating offshore wind turbines and software for autonomous space robotics are among the projects being supported. Get to know them: https://t.co/v98WKLG3lW

5

1

35

Machine Intelligence Group @ Edinburgh

@machine_group

3 years

Congratulations @henrygouk!

Royal Academy of Engineering

@RAEngNews

3 years

We are delighted to reveal the 17 new awardees receiving a #RAEngResearch Fellowship for 2022. Deep water mooring lines for floating offshore wind turbines and software for autonomous space robotics are among the projects being supported. Get to know them: https://t.co/v98WKLG3lW

0

5

Calum Heggan

@HegganCalum

4 years

Is few-shot meta-learning successful for general modalities? Find out how well your favourite meta-learner does in few-shot audio tasks in our new benchmark "MetaAudio"! https://t.co/a1VuWqPzod

1

18

23

Ivana Balazevic

@ibalazevic

4 years

I passed my PhD viva today with no corrections! 🥳 🥳 🥳 Many thanks to my examiners @_rockt and Mark Steedman for the very interesting and insightful discussion as a great way to finish my PhD @InfAtEd. Really excited to start @DeepMind on Monday! 😊

17

3

268

Linus Ericsson

@sillinuss

5 years

How Well Do Self-Supervised Models Transfer? Find out in our #CVPR presentation! Come chat with us in session 4 on Tuesday (11am EDT). Work done with @henrygouk & @tmh31. Paper: https://t.co/FbDQvqS0CO. Video: https://t.co/EpWdrPBk89. #CVPR2021 (1/n)

3

8

16

Edward Grefenstette

@egrefen

5 years

At ICLR? Interested in meta-learning? Come check out the WS on Learning to Learn tomorrow (Fri 6 May). I'll be giving a semi-contrarian talk about freeing our meta-learning algorithms from preconceived notions of what meta-learning is or should be. https://t.co/EBSS7yWB8t

1

13

48

Pulkit Agrawal

@pulkitology

5 years

Spreading the word: Consider submitting to ICRA'21 workshop on Learning to Learn for Robotics ( https://t.co/izQBXLP3yM) thanks to @yadrimz @_kainoa_ @sarahbechtle @YevgenChebotar and Timothy for organizing! Deadline is May 15.

sites.google.com

The workshop aim is to provide an informative overview of the existing challenges in using meta learning for robotics and set the grounds for future development.

1

4

24

Henry Gouk

@henrygouk

5 years

Good news everyone: my paper (w/ @tmh31 & Massi Pontil) on regularisation during fine-tuning has been accepted to #ICLR2021! Now I, too, will know the bittersweet experience of presenting at a virtual poster session! https://t.co/90LtW3KzI7

openreview.net

We investigate approaches to regularisation during fine-tuning of deep neural networks. First we provide a neural network generalisation bound based on Rademacher complexity that uses the distance...

1

3

24

Ivana Balazevic

@ibalazevic

5 years

Little is known of the latent semantic structure learned by knowledge graph representation models. We address this by drawing a connection to word embeddings in recent work (w/ @carl_s_allen & @tmh31, to appear #ICLR2021). 1/4 https://t.co/EnL3iBovgz

openreview.net

Many models learn representations of knowledge graph data by exploiting its low-rank latent structure, encoding known relations between entities and enabling unknown facts to be inferred. To...

2

22

96

Marija Jegorova

@MarijaJegorova

5 years

Delighted to brag - my paper 𝗨𝗻𝗹𝗶𝗺𝗶𝘁𝗲𝗱 𝗥𝗲𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻 𝗜𝗺𝗮𝗴𝗲 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝘄𝗶𝘁𝗵 𝗥𝟮𝗗𝟮-𝗚𝗔𝗡𝘀, won 1st prize in SPC @OCEANS_Conf. ArXiv: https://t.co/JtK4CgjUel Video: https://t.co/SP4DNQIWTJ #GAN #WomenInSTEM @machine_group @seebyte @InfAtEd

4

3

20

Marija Jegorova

@MarijaJegorova

6 years

Check out our virtual presentation for @icra2020! Video: https://t.co/BIMgybilFb ArXiv: https://t.co/ifQfdOdwRB We've developed a realistic GAN-based simulator for extremely high-dimensional sonar images! #ICRA2020 #ICRA @seebyte @machine_group

0

1

7

Marija Jegorova

@MarijaJegorova

5 years

Recorded a small video presenting our @OCEANS2020 paper on generating images of any chosen resolution with R2D2-GANs. Video: https://t.co/Vh1dFFBqQq Paper: https://t.co/3KIa8TMaCE @machine_group @seebyte #GANs #Sonar @womenroboticsed #WomenInSTEM

0

1

3

Ivana Balazevic

@ibalazevic

6 years

"Discriminative" semi-supervised learning makes use of the distribution over labels. We use a normalising flow to learn that distribution for arbitrarily complex labels: from one-hot vectors to binary vectors and images. Work with @carl_s_allen & @tmh31. https://t.co/y3Fr2gJIxD

0

4

17