hardmaru
@hardmaru
Followers
288,579
Following
1,471
Media
4,631
Statuses
26,759
Building Collective Intelligence @SakanaAILabs 🧠
Minato-ku, Tokyo
Joined November 2014
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
billie
• 362775 Tweets
Alito
• 293442 Tweets
Diddy
• 233505 Tweets
Diddy
• 233505 Tweets
Scottie
• 175236 Tweets
Crockett
• 136590 Tweets
#النصر_الهلال
• 100368 Tweets
سلمان
• 92239 Tweets
#วอลเลย์บอลหญิง
• 83624 Tweets
कन्हैया कुमार
• 58499 Tweets
Barron
• 52370 Tweets
Juventus
• 46424 Tweets
ابو عبيده
• 46275 Tweets
NCAA
• 41757 Tweets
Shani Louk
• 37465 Tweets
Usyk
• 24347 Tweets
رونالدو
• 23851 Tweets
Sean Combs
• 18747 Tweets
Madden
• 18458 Tweets
Tabilo
• 16893 Tweets
Kim Porter
• 13184 Tweets
كريستيانو
• 10473 Tweets
Pinned Tweet
New Paper Out.
Evolutionary Optimization of Model Merging Recipes
Our goal is not about training any particular individual foundation model. Instead, we think it makes more sense to create the machinery to automatically generate foundation models for us!
Introducing Evolutionary Model Merge: A new approach bringing us closer to automating foundation model development. We use evolution to find great ways of combining open-source models, building new powerful foundation models with user-specified abilities!
56
414
2K
43
182
921
This design is better than “𝕏”.
223
10K
101K
The opening line of David Goodstein’s textbook, “States of Matter” 🤯
Whats the best first sentence in a book you've read?
55
8
68
77
1K
8K
Pushing around these little robot soccer players, from DeepMind’s “Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning” paper.
304
737
4K
We're living in a cyberpunk future:
“Fooling automated surveillance cameras: adversarial patches to attack person detection”
54
2K
4K
QR codes created using Stable Diffusion and ControlNet. This is Art.
80
475
4K
A
#StableDiffusion
model trained on images of Japanese Kanji characters came up with “Fake Kanji” for novel concepts like Skyscraper, Pikachu, Elon Musk, Deep Learning, YouTube, Gundam, Singularity, etc.
They kind of make sense. Not bad!
お絵描きAI（Stable Diffusion）に漢字とその意味を1万字学習させて書き初めをさせました
順に「謹」「賀」「新」「年」です
26
2K
4K
112
793
4K
Interesting physics analogy of ML from the viewpoint of compression (
@elonmusk
)
“Physics formulas are compression algorithms for reality…If you ran physics simulation of the universe, eventually you will have sentience…At what point from hydrogen to us did it become sentient?”
140
569
3K
A fun way to learn about neural networks and AI is to implement a simulation game giving your agents little neural net brains, and training them using a simple method like evolution.
This demo trains a small neural network to drive around the track after only a few generations:
31
1K
3K
One of the most well-known pieces of software for downloading YouTube videos, “youtube-dl” was removed from GitHub following a takedown notice from the Recording Industry Association of America, or RIAA.
Someone encoded the source code into two images and put it on Twitter:
25
1K
3K
Announcing NeurIPS Preschool Track
This year, we invite preschoolers to submit machine learning research papers.
66
430
3K
This person took ~1700 pages of notes in mathematics lectures using LaTeX and Vim, and documented the workflow:
41
933
3K
Personal Announcement! I’m launching
@SakanaAILabs
together with my friend, Llion Jones (
@YesThisIsLion
).
is a new R&D-focused company based in Tokyo, Japan.
We’re on a quest to create a new kind of foundation model based on nature-inspired intelligence!
148
422
3K
Some personal news: After six years at Google, I decided it was time for me to leave and try something new again.
I had a fantastic time at Google Brain, and I’ll miss my friends, collaborators, and hanging out at the microkitchens!
137
46
3K
"Some rich people lost all their fortunes and became homeless"
#StableDiffusion2
#AIart
(Source: )
82
302
3K
Artificial lifeforms are super fascinating to watch.
These self-organizing, self-replicating, “lifeforms” emerged from a continuous time cellular automata system called Flow-Lenia.
Lenia is a family of CAs generalizing Conway’s Game of Life to continuous space, time and states.
33
532
3K
Teams of high school students built bottle-flipping robots for RoboCon 2018 in Japan
34
875
3K
New blog post: Collective Intelligence for Deep Learning
Recently,
@yujin_tang
and I published a paper about how ideas like swarm behavior, self-organization, emergence are gaining traction in deep learning.
I wrote a blog post summarizing the key ideas:
70
494
2K
Interesting application combining computer vision and high-powered lasers to eradicate weeds on a farm.
50
415
2K
Weight Agnostic Neural Networks 🦎
Inspired by precocial species in biology, we set out to search for neural net architectures that can already (sort of) perform various tasks even when they use random weight values.
Article:
PDF:
55
671
2K
Roman Emperor Project
Using GAN-based tools to help create photorealistic portraits of Roman Emperors from historical references
Project
Article
29
561
2K
MIT offers an excellent course on Deep Learning for Art, Aesthetics, and Creativity. All of the lecture videos are available on YouTube, with a fantastic list of speakers:
22
429
2K
How do you skim a research paper?
I usually read (in order):
1) abstract
2) 1st paragraph of the intro
3) last paragraph of intro (for contributions)
4) 1st paragraph of the conclusion (it's usually one paragraph anyways)
5) figures / tables of results, and read their captions.
47
333
2K
I'm blown away by the method and results in this paper. Progressive growing neural nets may be a trend we will see in 2018.
14
826
2K
If Google doesn’t get their act together and start shipping, they will go down in history as the company who nurtured and trained an entire generation of machine learning researchers and engineers who went on to deploy the technology at other companies… The modern day Bell Labs.
62
186
2K
I love the diversity of Tokyo’s urban architecture. This Tiny House is designed by Atelier Tekuto.
16
135
2K
"Anime scene of Yann Lecun at Bell Labs working on convolutional neural networks."
#StableDiffusion
36
151
2K
The most well-dressed snowball fight, colorized using deep learning.
19
344
2K
A series of blog posts on applying machine learning to architecture
Experiments:
Background:
20
506
2K
This amazing book on the foundations of machine learning is now available for free from Microsoft as a PDF download. I learned so much from this book over the years, and I feel that much of the material is still relevant. The solutions to the exercises also seem to be available!
"Pattern Recognition and Machine Learning" by
@ChrisBishopMSFT
is now available as a free download. Download your copy today for an introduction to the fields of pattern recognition & machine learning:
#ML
#Insights
26
2K
3K
13
561
2K
Face to Anime using AnimeGANv2
12
367
2K
Papers with Code: A searchable site that links machine learning papers on ArXiv with code on GitHub. They also tag any framework libraries used, along with other info like GitHub stars. I think such a feature would be a nice addition to ArXiv-Sanity.
9
635
2K
Fooling Facial Detection with Fashion
Nice article surveying common face detection methods, and tests practical implementations of adversarial patches on a face mask for fooling them. h/t
@MelMitchell1
15
507
2K
High resolution inpainting experiment with
#StableDiffusion2
Transporting the famous Futaba Sushi restaurant in Ginza, Tokyo, to other cities, countries, planets, and finally, to a galaxy far far away…
#StableDiffusion
#AIart
29
300
2K
A.I. camera mistakes referee’s bald head for ball, follows it through the match.
49
341
2K
“First Order Motion Model for Image Animation” hooked up to a live camera:
Original NeurIPS2019 paper / code:
14
334
2K
OpenAI, Google & Anthropic ban the use of the generated output content from their AI models to train other AI models, under their terms-of-service. However, they’ve been using other online content for their own model training. They can’t have it both ways.
52
379
2K
One year after building rock solid technical infrastructure for your machine learning research project
18
205
2K
This
#StableDiffusion
add-on for Blender looks amazing.
@AI_Render
renders an AI-generated image based on a text prompt and your scene in Blender.
19
346
2K
Reinforcement Learning for Improving Agent Design: What happens when we let an agent learn a better body design together with learning its task?
article:
pdf:
23
425
2K
Being able to fool AI detection algorithms IRL will be an important survival skill in the 21st century 👻
In other news, our latest work made its way onto Japanese national TV this week! 🚘
17
1K
5K
34
250
2K
LIMA, a 65B LLaMa fine-tuned only with supervised learning on 1000 curated examples, without any RLHF, demonstrates remarkably strong performance, generalizes well to unseen tasks not in training data. Comparable to GPT-4, Bard, DaVinc003 in human studies.
25
245
2K
An interactive article explaining why weight initialization is so important for training neural nets by
@deeplearningai_
, written in the format.
4
485
2K
Uber developed a system of nested hexagons to represent space, called H3:
68
198
2K
I’m super excited to see ideas from complex systems such as swarm intelligence, self-organization, and emergent behavior gain traction again in AI research. We wrote a survey of recent developments that combine ideas from deep learning and complex systems:
27
306
2K
Jupyter notebooks with Python examples for reproducing examples from each chapter of Christopher Bishop's “Pattern Recognition and Machine Learning” textbook (also available for free in link above)
9
444
2K
Academic Torrents is a distributed system for sharing enormous datasets. So far they have made 27.23TB of research data available.
6
570
1K
The map of the brain, created by an aerospace engineer.
These are the result of six years of research. It’s always interesting to me to view the perspective of one challenging scientific field through the lens of an expert from another field. 🧠
Source:
32
322
1K
Self-attention mechanism can be viewed as the update rule of a Hopfield network with continuous states.
Deep learning models can take advantage of Hopfield networks as a powerful concept comprising pooling, memory, and attention.
21
380
1K
Using deep learning to implement linear regression
A skilled excavator operator with a Engcon EC206 tiltrotator.
10
223
1K
14
323
1K
Decoding the Enigma with RNNs. They trained a LSTM with 3000 hidden units to decode ciphertext with 96%+ accuracy.
12
793
1K
Dive into Deep Learning: An interactive deep learning book with code, math, and discussions, based on the NumPy interface. I really like the format of the textbook!
14
349
1K
TinyML and Efficient Deep Learning Computing
MIT 6.5940 ()
“This course will introduce efficient AI computing techniques that enable powerful deep learning applications on resource-constrained devices. Topics include model compression, pruning,
22
233
1K
Conventional thinking: Build a robot to solve the problem.
Out-of-the-box thinking: Get the problem to solve itself.
Example: Self-solving Rubik's Cube by
@takashikaburagi
15
293
1K
Japan recently reaffirmed that it will not enforce copyrights on data used in AI training.
The policy allows AI to use any data “regardless of whether it is for non-profit or commercial purposes, whether it is an act other than reproduction, or whether it is content obtained
54
301
1K
Falcon-40B, a state-of-the-art large language model, trained on a massive English web dataset called RefinedWeb, has now been released by
@TIIuae
under a truly permissive open-source license (Apache 2.0)‼️
This is a big step forward for Open-Source AI. 🎊
14
253
1K
Recently I’ve been tweeting more about the
#HongKongProtests
and less about my views on machine learning and artificial intelligence.
I apologise for the inconvenience ...
85
161
1K
I’m so tired of AI hype tweets. They’re all over my Twitter feed these days.
Really striking how every AI hype tweet is explicitly trying to induce FOMO. "You're getting left behind. All your competitors are using this. Everyone else is making more money than you. Everyone else is more productive. If you're not using the latest XYZ you're missing out."
166
697
5K
40
141
1K
Some people asked me how I got into machine learning research
In other news, someone crashed the Chanel show on the final day of Paris Fashion Week. She blended in so well the security had a difficult time finding her.
114
6K
11K
15
169
1K
