Tim Kietzmann
@TimKietzmann
Followers
11,075
Following
2,623
Media
544
Statuses
6,508
ML meets Neuroscience #NeuroAI , Full Professor at the Institute of Cognitive Science ( @UniOsnabrueck ), prev. @DondersInst , @Cambridge_Uni #neuroconnectionism
Joined October 2016
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
Ronaldo
• 713543 Tweets
Portugal
• 579000 Tweets
Venezuela
• 379361 Tweets
#loveislandusa
• 72960 Tweets
#SmackDown
• 64646 Tweets
George Stephanopoulos
• 51052 Tweets
Bleach
• 48264 Tweets
Air Force One
• 47658 Tweets
Rondon
• 40175 Tweets
Serena
• 40159 Tweets
#CopaAmerica2024
• 37633 Tweets
Yankees
• 33299 Tweets
選挙妨害
• 32781 Tweets
リンツのチョコ
• 32096 Tweets
Kenny
• 31590 Tweets
Ram Rahim
• 26606 Tweets
Self Esteem
• 22718 Tweets
#ManoTengoFe
• 16040 Tweets
京都大作戦
• 15935 Tweets
Romo
• 14226 Tweets
Braves
• 13803 Tweets
Laura Loomer
• 13283 Tweets
サラダ記念日
• 11744 Tweets
MAIARA TE AMAMOS
• 10065 Tweets
Pinned Tweet
Years in the making: 304 papers cited in a huge effort to characterise this emerging field that we hold dearly.
Read this paper to find out what we are doing, why and how, and why we think that ANNs are a central tool for understand brain computations.
#neuroconnectionism
The neuroconnectionist research programme — a Perspective by
@AdrienDoerig
@rowansommers
@kateiyas
@tyrell_turing
@neurograce
Jenann Ismael
@KordingLab
@talia_konkle
@marcelge
@KriegeskorteLab
@TimKietzmann
2
62
172
2
36
193
It has finally happened, I was invited to review my own paper.
100
112
4K
Ran one of our essay questions through
@OpenAI
's new chatbot. Essays are dead.
Back to hand-written exams I guess. Sigh.
85
264
2K
Nice Illustration that our visual system expects certain stereotypical poses and the incoming data is fit to that internal model.
28
227
2K
If this does not mess with your visual system, I don't know what will...
19
333
1K
Just finished my course “Machine Learning for Cognitive Computational Neuroscience”. Across 12 lectures (90 minutes each) and 10 workgroup sessions, we covered >100 papers (46% published in the past two years). The students (and I) learned a lot.
Here is what we covered: 1/
28
181
1K
Fun fact: this is the amount of brain tissue that has as many neurons as AlexNet has units.
18
91
994
Original from here:
3
15
910
Apparently, at some level of ML fame, you become a neuroscience expert overnight.
17
39
612
🥳 My lab was awarded 1.5M Eur by
@ERC_Research
for our
#ERCStG
proposal
#TIME
. Over the next five years we will take a deep dive into visual information sampling, extraction, and integration by combining neuroimaging, psychophysics and large scale machine learning. So excited!
46
16
625
🚨Major professional news: My lab will leave the Donders and transition to the Institute of Cognitive Science at
@UniOsnabrueck
, where I will take on the role of Full Professor for neuro-inspired Machine Learning. 1/4
67
15
592
Turns out, scanning a Broccoli looks a lot like fireworks...
8
264
540
Brains on artificial vs natural stimuli.
5
80
494
New preprint alert! We show that predictive coding is an emergent property of input-driven RNNs trained to be energy efficient. No hierarchical hard-wiring required. A thread: 1/
15
182
495
Don't these look perfect together? The results of 3D printing my wife's and my brain. It's not weird, it's
#RomanticNeuroscience
17
82
455
In other news, I just received THE LETTER: tenured at the
@DondersInst
/
@AI_Radboud
. Could not be happier! 🍾
56
0
489
Tweeps, I am hiring (big time) - please spread the word.
I am looking for three postdocs in the space of neuro-inspired ML and cognitive computational neuroscience to join us at the Institute of Cognitive Science (
@UniOsnabrueck
).
Here is why this is a great opportunity: 🧵
10
279
428
"The majority of good ideas [towards human-level AI] will come from academia.
Even if the most impressive applications come from industry."
- Yann LeCun
@ylecun
14
44
431
@willjharrison
@OpenAI
Not this one, no, but after a great suggestion by
@__init_self
, we tried to push it to its limits with something more creative. I am blown away to say the least.
7
48
383
I spent the day laughing at the false positives of a DNN trained to detect NSFW material.
I probably should do an exhibit on them. Name suggestions?
28
36
352
Are you using DNNs in your work? Then our new paper may be of interest to you: "Individual differences among deep neural network models", now out in
@NatureComms
:
A quick run-through:
5
107
321
New paper & resource alert: our ecoset project is finally out and you are all invited to use it. A thread. 1/n
10
88
312
Happy little goat hidden in a Kookaburra. Once you see it...
7
30
261
Thrilled to announce that I just accepted an offer from the
@DondersInst
@AI_Radboud
! I will join their faculty as Assistant Professor this fall.
Get in touch if you would like to work with me in the area of (visual) computational neuroscience and machine learning!
33
22
239
PSA: Academia can be a harsh place, but it does not have to be.
- Celebrate beautiful work and findings by others.
- Read a paper that you liked? Let the authors know.
- Remember: science is not a zero-sum game.
#ScienceTogether
#ForwardTogether
#AcademicChatter
2
36
209
What is your favourite "ANN contributing to brain science" paper? Bonus points for NOT VISION: language, motor control, audition, planning, RL,... anything goes.
Background: I am putting together a lecture series and noticed how incredibly biased my examples are.
36
36
212
Dear ML/Neuro/AI/CogSci researchers from Ukraine - my lab will welcome you with open arms. Get in touch, my DMs are open.
#ScienceForUkraine
1
60
199
Just stumbled upon an old letter to the editor in which we respond to the reviewer's request to cite 6 (!) of his/her own papers.
Adding 2/6 in round 1 was not enough. We were told that the reviewer cannot accept until all 6 are added.
DON'T DO THIS TO PEOPLE.
17
25
174
Now out in PNAS!
We combine MEG source reconstruction, RSA, and end-to-end deep neural network training to show that "Recurrence is required to capture the representational dynamics of the human visual system".
#deeplearning
#neuroscience
#neuroimaging
New paper: Recurrence is required to capture the representational dynamics of the human visual system by
@TimKietzmann
et al.
4
61
160
1
53
170
My whole timeline has become more or less useless and boring: it's all talk about chatGPT and some hastily coded-up startups trying to cash in - all sensible research discussion has gone to the background.
16
5
167
Instead of flying, the lab is happily taking the train from Osnabrück to Oxford. Excited for
#CCN2023
@CogCompNeuro
6
3
172
New preprint from the lab: "Individual differences among deep neural network models."
Work with
@KriegeskorteLab
,
@HannesMehrer
, and Courtney Spoerer.
#tweeprint
below. 1/7
4
61
152
My son figured out that he can make the biggest mess, declare it "an experiment", and totally get away with it because HOW CAN I NOT ALLOW EXPERIMENTS IN THIS HOUSE?
8
3
152
Excited that our paper "Predictive coding is a consequence of energy efficiency in recurrent neural networks" is now out in
@Patterns_CP
! Much has changed since preprint, so check it out:
Work with the fantastic
@hellothere_ali
,
@nasiryahm
, and
@marcelge
!
3
47
158
"Cognitive Computational Neuroscience" in the eyes of VQGAN and CLIP. Quite accurate if you ask me.
5
25
143
*slaps roof of neural network*
"This bad boy can fit 1.3 million datapoints with only 80 million parameters."
2
7
129
The Cognitive Computing AI MSc program at the Donders is dropping reference letters from the application process. We hope that this will reduce bias and lead to fairer evaluations of people of diverse backgrounds.
4
10
132
German university students knock on their tables after a lecture to show their appreciation. It's a small gesture, but man it feels great.
2
5
130
The lab has been scooped repeatedly in the last few weeks. Positive: we operate in a space of ideas that people find interesting. Negative: boy it sucks.
11
1
131
Help me out hive mind: is there a good twitter list of people in the interdisciplinary space of ML/Comp Neuro/AI?
If not, feel free to suggest people in this thread, trying to diversify my timeline. Bonus poins for researchers from underrepresented groups.
18
9
124
Asked a deep net to dream up a "Kietzmann lab". Perhaps a bit bigger than I had wanted, but the setting sure is spectacular.
9
5
128
When it comes to academic publishing: quality over quantity.
10
11
125
Interesting data. A PhD in natural sciences in Germany takes on average 4.7 years - and yet, most scholarships last only three.
Der Bundesbericht Wissenschaftlicher Nachwuchs 2021 ist da:
"Die durchschnittliche
#Promotionsdauer
beträgt 5,7 Jahre (ohne Humanmedizin/Gesundheitswissenschaften)." (S. 137f., )
#BuWiN2021
12
68
207
2
26
123
🚨HIRING🚨 We are looking for a postdoc in the space of machine learning and visual computational neuroscience to join my group at the institute of cognitive science (position for 3 years, can be extended). Official call here (more info in the🧵 below):
Tweeps, I am hiring (big time) - please spread the word.
I am looking for three postdocs in the space of neuro-inspired ML and cognitive computational neuroscience to join us at the Institute of Cognitive Science (
@UniOsnabrueck
).
Here is why this is a great opportunity: 🧵
10
279
428
1
86
123
Finally out: Our review paper on Deep Neural Networks in Computational Neuroscience (w
@KriegeskorteLab
and Partick McClure) - please RT.
#Neuroscience
#DeepLearning
#AI
#ComputationalNeuroscience
#CogSci
2
64
118
Thrilled to see this out. We show that recurrent DNNs can outperform parameter-matched feedforward DNNs in large-scale object classification, trade off speed for accuracy, and better predict human reaction time data.
New from Spoerer and colleagues: "Recurrent neural networks can explain flexible trading of speed and accuracy in biological vision" -
@KriegeskorteLab
@TimKietzmann
0
12
33
4
36
120
Preparing a first-year lecture on computational modelling. Thanks to
@IrisVanRooij
@PaulMinda1
@le_Tomassini
@mariekewoe
@LizBonawitz
and
@o_guest
, I now have a perfect slide to start a discussion on what it actually is. Cheers!
2
25
112
Don't be fooled by the grants that I got
I'm still, I'm still Timmy the postdoc.
3
1
117
Please advise: Which female PIs or senior researchers in AI or neuro-AI are located in the EU? Looking for inspiration for a keynote speaker outside my regular bubble.
Please RT for visibility. Thx!
55
130
115
Who needs to constantly look up the correct spelling for arXiv, PsyArXiv, bioRxiv? Or is it just me?
5
0
109
I am speechless. The
@Radboud_Uni
executive board has sent me these amazing flowers to our home in Germany to congratulate me on the ERC. Thank you so much! This is leadership par excellence.
0
0
113
I was asked to review A WHOLE BOOK for a for-profit publisher. What do they offer in return?
"For well-prepared review reports submitted in a timely manner, we provide discount vouchers for future publications by MDPI."
Wow.
4
5
105
Seriously, what the hell? This is incredibly strong for me. Needed to actually draw the circles to believe it.
7
16
97
Okay, I'll bite. Letters of reference (for MSc students and likely beyond) are utter nonsense, often written by the students themselves and signed off by a professor who barely knows them. Worst of all: their very existence discriminates against minorities and amplifies biases.
12
4
100
6
14
92
New preprint: “Recurrence required to capture the dynamic computations of the human ventral visual stream.” with Courtney Spoerer,
@LynnKASorensen
, Radoslaw Cichy,
@OlafHauk
,
@KriegeskorteLab
#MEG
#DeepLearning
#Neuroscience
#ComputationalNeuroscience
1/10
2
48
96
🚨ERC Job Alert 🚨
Are you looking for a PhD position? Are you into AI and/or computational/cognitive neuroscience? Then consider becoming an ERC funded graduate student with us:
I am biased, but I think this is a great opportunity. 🧵
4
77
106
The talks of the CVPR Neurovision workshop ("What can computer vision learn from visual neuroscience?") are now online!
1
16
98
MSc programs at Radboud often require students to upload a photo of themselves as part of their application.
I have no idea what the looks of a student have to do with their academic potential. The Cognitive Computing MSc AI program will therefore not follow suit.
4
4
94
Due to time constraints, I would have had to fly in, give the talk, and fly out again - a bad ratio of CO2 vs time spent interacting with other scientists.
So a big thank you to the
@mrccbu
for experimenting with me and having me over digitally. Worked like a charm.
Now onto the final session, we’re discussing how computational models are useful for studying the ventral stream.
@TimKietzmann
is our first speaker and giving his talk via Skype!
0
0
8
2
5
92
Ever wonder what the
@neuromatch
academy looks like? Don't worry, this GAN and I have got you covered.
2
9
93
3
14
86
Tried to argue with admin that a good coffee machine will increase the productivity of the team way more than a single additional GPU ever could.... and was 100% unsuccessful.
17
0
91
As some of you have asked, here is a link to my CCN keynote from this year.
Main topic: how we use ANNs as a language to describe, implement, and test theories of brain computations.
#neuroconnectionism
3
17
91
I'm curious. Who ever said vision is "solved"? We teach AI students in their very first semester that DNNs remain far from human performance/robustness.
This one figure is pretty much a final nail to the coffin of the preposterous idea that deep learning somehow "solved" vision. Paper:
Thx
@MaxALittle
for posting ()
6
25
121
8
12
88
The children and I made a real world chart to see which colours they prefer using.
#SundayMorningDataVis
#DataIsBeautiful
4
2
85
We ran a 'meme contest' in my course "ML for Cognitive Computational Neuroscience".
Student submissions were... niche. They were nerdy, they were well informed, they were brilliant, and so very funny.
Have two examples, it's Friday.
#CoxiOS
1
1
85
Alright, could we all agree to show figures in the main text of preprints (even if you decide to play along with anachronistic policies for your journal submission)?
2
5
80
The feeling of an ML lecturer seeing their students only ever use DNNs.
1
16
81
So I bought a whiteboard for my home-office and it's the BEST purchase in a long while.
Here is why: first, I cannot meet without drawing, and I now point the webcam at the board during online meetings to aid discussion. 1/3
3
1
80
After being scattered across Europe for the past 1.5 years, the lab is finally embarking on a joint retreat. I cannot overstate how much I am looking forward to this. Beautiful spot, too.
5
0
82
Told my wife that my current level of crazy busy "is just a phase". She could not stop laughing and responded that I've been saying this for 15 years.
Time to face reality I guess.
4
0
85
I present to you: our 4 year old.
Her: "I'm sorry that you have to work again daddy".
... door closes ...
... 10 seconds...
... head pokes back in ...
Whispering: "Don't worry, you don't have to work when you are dead".
You could not make this stuff up.
4
1
76
Bored of all the dogs in ImageNet (ILSVRC)? Meet ecoset: 1.5m images from 565 basic level categories (selected to be of importance to humans). A new benchmark for
#ComputerVision
,
#ML
, and
#DeepLearning
.
Dataset and pre-trained CNNs here:
1
18
79
This is brilliant: successful predictions of conference paper acceptance from paper appearance alone.
Hidden gem: algorithm predicts its own paper to be rejected without peer review.
7
9
81
Can you lot please take a break publishing interesting papers? I am way behind with my reading. Thanks.
4
0
78
Would anyone mind sharing their setups for having a (power)nap in the office? Asking for a friend with small children who have absolutely no respect for their parents' sleep.
35
0
81