With a $65M investment led by SoftBank, Tractable is set to expand its AI-driven property and car damage appraisal services, revolutionizing the insurance claim processing landscape.

Read more: https://trendotech.com/2023/07/18/ai-innovator-tractable-acquires-65m-investment-for-enhanced-damage-appraisal-platform/

#InsurtechInnovation #Tractable #AIDamageAppraisal

With a $65M investment led by SoftBank, Tractable is set to expand its AI-driven property and car damage appraisal services, revolutionizing the insurance claim processing landscape.

Read more: https://trendotech.com/2023/07/18/ai-innovator-tractable-acquires-65m-investment-for-enhanced-damage-appraisal-platform/

#InsurtechInnovation #Tractable #AIDamageAppraisal

Finally, I managed to write another blog post. In the post I am essentially talking about works (mostly) by Alessandro Rudi and coauthors on #tractable #probabilistic models such as #mixtures with #negative parameters.

Check out: https://trappmartin.github.io/website/post/2023_06_snf/

I will likely go into details of some of the aspects of this new family of models in follow up posts.

Let me know what you think about the blog post. Too high level or just right? Or any other feedback?

I'm back in Helsinki and super excited about my course on #tractable #probabilistic modelling at #aaltouniversity! Looking forward to explore the space and limitations of #tractable computations in #probabilisticmodels with students.

I’m excited to be organising a special #course on #tractable #probabilisticmodelling at #AaltoUniversity at the end of this term.

Please consider joining if you are at Aalto and interested in the topic.

Because I moved instances some time ago, a short re-#introduction.

I am a postdoctoral researcher at Aalto University studying topics at the intersection of #tractable models (probabilistic circuits), #deeplearning, and #Bayesian methods with a focus on #nonparametrics. My goal is to develop and understand methods that are highly flexible & adaptive but allow tractable probabilistic inferences. I do a lot of #Bayesian stuff and care strongly about priors.

See: https://trappmartin.github.io

How?

SPLs realize a #tractable product of #experts via 2 #circuits.

One encodes an #expressive distribution over the labels, the other compactly #compiles the #symbolic #constraint!

We can compute #exact #gradients because we can normalize them in one feedforward pass!

This can be of interest to many #probabilistic folks!

cc @nbranchini @avehtari @PhilippHennig

5/

An #introduction toot! I'm Steven, a second-year PhD student at the AIML Lab TU Darmstadt, supervised by Kristian Kersting. My research topics focus on #deep #tractable #probabilistic modeling with a particular interest in #probabilistic #circuits.

I am a #Lecturer (Assistant Prof) in #ML at the University of #Edinburgh.

I research how #deep #probabilistic #models can be #reliable and can do #complex #reasoning with #guarantees in the real world and with #constraints.

Will toot about #automating #tractable #neuro #symbolic #AI and its #hype, #CS and #probabilistic #programming but also anything from #music to #politics and #fightsforrights.

My apologies in advance!

#introduction

Hello everyone out there in the fediverse!

I'm currently a Academy of Finland postdoctoral fellow at Aalto University working on probabilistic #machinelearning. Most of my interests are related to probabilistic #machinelearning methods that are flexible (#nonparametric), efficient (#tractable), and exact or come with guarantees (or a subset of thereof).

In my research, I work a lot with #JuliaLang and I'm always eager to learn new things.

Curious to see where this all goes.

#introduction