OttoConnecting mastodon users in #SouthAfrica. Comment or boost if you're one of us.
RonRichman
- 21 Followers
- 84 Following
- 12 Posts
Interested in the application of deep learning within actuarial work.
Nassim Nicholas TalebLet's see what happens on this site.
πππππ πΆππππππ π1: #Tokyo metro map in 2D.
2: The same map in 3D.
2: The same map in 3D.
Jascha Sohl-DicksteinIf there is one thing the deep learning revolution has taught us, it's that neural nets will outperform hand-designed heuristics, given enough compute and data.
But we still use hand-designed heuristics to train our models. Let's replace our optimizers with trained neural nets!
But we still use hand-designed heuristics to train our models. Let's replace our optimizers with trained neural nets!
Richard McElreath π¦I am a harmless wandering anthropologist, bringing 20 hours of free #CausalInference and #BayesianStatistics instruction to your door. From foundations of inference through DAGs, #MultilevelModels & poststratified causal effects to #GaussianProcesses, Bayesian imputation & ODEs. Theatrical trailer below. Playlist: https://www.youtube.com/playlist?list=PLDcUM9US4XdMROZ57-OIRtIK0aOynbgZN
Statistical Rethinking 2022
Leshem Choshen@RonRichman it benefits from larger datasets so in that sense I would say not too much. It is clear that similar starting point is crucial (although some works claim aligning the right neurons is enough to allow reasonable fusing even without it).
NancyGPTI have seen people reflecting on the parallels between USENET and Mastodon.
A million (25) years ago I wrote a book about community on USENET. If youβre not familiar and want a primer, this might be a fun time to read it.
The parallel is good, if imperfect. Understanding the old internet can only make you wiser about understanding todayβs.
Recycling Finetuned models, it works!
Finetuned models lie everywhere,
there must be a way to use the data and compute invested in them.
Apparently averaging their weights is such a method.
3 papers & Aπ§΅