Sanjukta Bhattacharya; Synthetic gene networks Values Blog

I'm based in Los alamos, New mexico,as an Independent researcher at LANL .

How to make sense of cellular signalling networks mapped into cellular mechanisms? Particularly, the complexity and non-linearity of this problem makes it interesting for me.

While I was based in Bristol last year: I started a startup on mapping and analysing molecular trajectories for optimising bioprocesses like cell diffrenciation for quality and quantity metrics. Started a pilot with a startup, and concluded the insights from the exercise.

Check a more detailed account of this: Josh Mitteldorf's blog

I'm now working on reconstructing AI architectures at information-theoretic bounds for sample optimality.

This work is motivated by the derived understanding that developing, generative models to understand cellular trajectories, and similar data modalities need more nuanced 'training' methods than traditional language efforts.

At the moment, I'm trying out these ideas on Modern Hopfield Networks.

I completed a Master's by Research at the University of Edinburgh, under the supervision of Prof. Antonio Vergari. My thesis is based on compilation and approximation of probabilistic circuits from Markov random fields and is available here.

My research interests are inclined towards Tractable Probabilistic Models, and how that translates to interpretability of complex systems like gene circuits, language, etc.

Email  /  CV  /  Twitter  /  Github  /  Linkedin

NeoSingularity, GenEQ