Wouter Nuijten

32 posts

Wouter Nuijten

Wouter Nuijten

@wouterwln

PhD student Bayesian Machine Learning & Active Inference @TUeindhoven . Football & Futsal enthousiast

Eindhoven, Nederland Katılım Şubat 2022
74 Takip Edilen39 Takipçiler
Wouter Nuijten retweetledi
Lancelot Da Costa
Lancelot Da Costa@lancelotdacosta·
Looking for prospective students & collaborators to work towards *An Agent Foundation Model*! 👨‍💻👩‍💻 Keywords: Active model discovery, active learning & model based planning. More details: lancelotdacosta.com/research (bottom of page). If you’re interested, get in touch! 💡
English
0
7
50
5.7K
Wouter Nuijten
Wouter Nuijten@wouterwln·
Recently at @lazydynamics, we needed a fine-grained scheduler, coupled to the machine clock, to build our multi-scale agents. To streamline development, I built `Gears.jl`, available now at github.com/lazydynamics/G…. We chose to make it public, so let me know what you think!
English
0
1
3
111
Wouter Nuijten
Wouter Nuijten@wouterwln·
What's even nicer: because our method injects priors locally, everything still works within @ReactiveBayes ' RxInfer.jl using message passing. Special thanks to my colleagues at @LazyDynamics for making this possible!
English
0
1
4
195
Wouter Nuijten
Wouter Nuijten@wouterwln·
In Active Inference, a lot of time is spent on computing Expected Free Energy. What if we could tweak the generative model such that EFE can be minimised with traditional variational inference methods?
English
1
3
6
361
Wouter Nuijten retweetledi
Bert de Vries
Bert de Vries@bertdv0·
Agreed with @fchollet on FEP (t.ly/s4gMV), but FEP is more than a pretty good idea, and there are more benefits to realizing an agent as an active inference (AIF) process beyond active data selection. I will mention a few below:
English
1
9
25
1.5K
Wouter Nuijten retweetledi
Bert de Vries
Bert de Vries@bertdv0·
New paper alert! Active Inference (AIF) agents score policy candidates using a cost function called the Expected Free Energy (EFE), which has many desirable features, such as a parameter-free balance between information-seeking and goal-driven behavior. (1/4)
English
2
9
28
1.9K
Wouter Nuijten retweetledi
ReactiveBayes
ReactiveBayes@ReactiveBayes·
Turns out .ml doesn’t just stand for machine learning - it also means maybe lost :/ But hey, every project needs its "we lost our domain" story. Our just happened on Friday. Find us at rxinfer.com now. This time for real (probably).
ReactiveBayes tweet media
English
0
2
7
271
Wouter Nuijten
Wouter Nuijten@wouterwln·
Catch me at @NeurIPSConf in Vancouver, BC this week! I will be at the conference all week, so feel free to hit me up for a drink (or five)! Saturday, I will present a poster at the Bayesian Decision Making workshop.
English
0
0
4
85
Wouter Nuijten
Wouter Nuijten@wouterwln·
Absolutely thrilled to announce that our work “Riemannian Black Box Variational Inference” has been accepted at the NeurIPS Workshop on Bayesian Decision-Making and Uncertainty! See you in December in Vancouver ;) openreview.net/pdf?id=QBbc0L5…
English
2
2
8
449
Wouter Nuijten
Wouter Nuijten@wouterwln·
Also, this week I am at @iwai_ws in Oxford to talk about Active Inference, so hit me up for a Free Energy Chat ;)
English
0
0
3
81
Wouter Nuijten retweetledi
ReactiveBayes
ReactiveBayes@ReactiveBayes·
🚀 Calling all Bayesian enthusiasts! @ReactiveBayes needs YOU to shape the future of reactive, efficient & scalable inference. Join us in building Bayesian-driven autonomous agents with RxInfer.jl. Fork, contribute, discuss at rxinfer.ml #BayesianInference #Julia
English
0
11
17
2.2K
Wouter Nuijten
Wouter Nuijten@wouterwln·
Catch me at @JuliaConOrg in my hometown of Eindhoven this week! I will be presenting twice on Friday and strolling around the Philips Stadium tomorrow and Thursday !
English
1
0
6
84
Wouter Nuijten
Wouter Nuijten@wouterwln·
Today, I was a guest in a workshop hosted by @InferenceActive on RxEnvironments.jl, demoing the basics of the package and answering lots of interesting questions. Recording is available at youtu.be/ygmAhA18mkQ?fe…. Thanks Daniel & co for having me!
YouTube video
YouTube
English
0
1
6
777
Wouter Nuijten
Wouter Nuijten@wouterwln·
@AlbertPdsnk @sirbayes @dmdohan @bvdmitri For example, we know the order in which variables are created, and we know that people tend to write their generative models in the same order as they'd want to see it drawn (left to right, top to bottom). We could use that heuristic as a starting point
English
0
0
0
51
Wouter Nuijten
Wouter Nuijten@wouterwln·
@AlbertPdsnk @sirbayes @dmdohan @bvdmitri Honestly, I think we can make a serious attempt towards this. We have a lot of implicit knowledge about the graph structure without needing additional user specification. Would be interesting to see what a naive solution would look like.
English
1
0
0
48
Kevin Patrick Murphy
Kevin Patrick Murphy@sirbayes·
This is my semi-periodic request to VLM gurus: when will I be able to upload an image such as the one below and have {ChatGPT, Gemini, Whatever} give me back tikz code that reconstructs the figure? I would pay >$20/month for that! (@dmdohan knows :)
Kevin Patrick Murphy tweet media
English
23
9
187
57.1K