About

Ryan P. Adams is a principal investigator at the Laboratory for Intelligent Probabilistic Systems within the Princeton University Department of Computer Science. His research focuses on thermodynamic computing, leveraging the natural dynamics of small-scale nonlinear physical systems coupled to thermal baths for generative modeling. While his platform-agnostic approach allows for broad applications, he has a primary interest in networks of nano- and opto-mechanical resonators, exploring their potential for energy-efficient computation. Beyond thermodynamic computing, Adams investigates how physical systems can be harnessed for computation, including simulating classical wave equations on quantum hardware and embedding control and sensing in mechanical metamaterials for robotics. His work aims to understand and develop novel computational paradigms that utilize physical phenomena, contributing to the advancement of energy-efficient and physically grounded computational methods.

Research topics

• Computer Science
• Machine Learning
• Artificial Intelligence
• Quantum mechanics
• Microbiology
• Physics
• Mathematics
• Structural engineering
• Mathematical analysis
• Biochemistry
• Optics
• Chemistry
• Composite material
• Biology
• Algorithm
• Engineering
• Genetics
• Materials science
• Programming language

Selected publications

• Diverse events have transferred genes for edible seaweed digestion from marine to human gut bacteria

  Cell Host & Microbe · 2022 · 79 citations

  • Biology
  • Microbiology
  • Genetics
  DOI

• A Multi-Objective Active Learning Platform and Web App for Reaction Optimization

  Journal of the American Chemical Society · 2022 · 182 citations

  • Computer Science
  • Computer Science
  • Machine Learning

  We report the development of an open-source experimental design via Bayesian optimization platform for multi-objective reaction optimization. Using high-throughput experimentation (HTE) and virtual screening data sets containing high-dimensional continuous and discrete variables, we optimized the performance of the platform by fine-tuning the algorithm components such as reaction encodings, surrogate model parameters, and initialization techniques. Having established the framework, we applied the optimizer to real-world test scenarios for the simultaneous optimization of the reaction yield and enantioselectivity in a Ni/photoredox-catalyzed enantioselective cross-electrophile coupling of styrene oxide with two different aryl iodide substrates. Starting with no previous experimental data, the Bayesian optimizer identified reaction conditions that surpassed the previously human-driven optimization campaigns within 15 and 24 experiments, for each substrate, among 1728 possible configurations available in each optimization. To make the platform more accessible to nonexperts, we developed a graphical user interface (GUI) that can be accessed online through a web-based application and incorporated features such as condition modification on the fly and data visualization. This web application does not require software installation, removing any programming barrier to use the platform, which enables chemists to integrate Bayesian optimization routines into their everyday laboratory practices.

  DOI

• Bayesian reaction optimization as a tool for chemical synthesis

  Nature · 2021 · 965 citations

  • Computer Science
  • Computer Science
  • Machine Learning
  DOI

• A data-driven computational scheme for the nonlinear mechanical properties of cellular mechanical metamaterials under large deformation

  Soft Matter · 2020 · 51 citations

  • Computer Science
  • Artificial Intelligence
  • Computer Science

  Cellular mechanical metamaterials are a special class of materials whose mechanical properties are primarily determined by their geometry. However, capturing the nonlinear mechanical behavior of these materials, especially those with complex geometries and under large deformation, can be challenging due to inherent computational complexity. In this work, we propose a data-driven multiscale computational scheme as a possible route to resolve this challenge. We use a neural network to approximate the effective strain energy density as a function of cellular geometry and overall deformation. The network is constructed by "learning" from the data generated by finite element calculation of a set of representative volume elements at cellular scales. This effective strain energy density is then used to predict the mechanical responses of cellular materials at larger scales. Compared with direct finite element simulation, the proposed scheme can reduce the computational time up to two orders of magnitude. Potentially, this scheme can facilitate new optimization algorithms for designing cellular materials of highly specific mechanical properties.

  DOI

Recent grants

• RI: Small: Parallel Methods for Large-Scale Probabilistic Inference

  NSF · $433k · 2017–2020

• RI: Small: Parallel Methods for Large-Scale Probabilistic Inference

  NSF · $450k · 2014–2018

• RI: Small: Accelerating Machine Learning via Randomized Automatic Differentiation

  NSF · $450k · 2020–2024

• Lagging or Leading? Linking Substantia Nigra Activity to Spontaneous Motor Sequences

  NIH · $1.9M · 2015–2019

Frequent coauthors

• Matthew Johnson

  Florida Institute for Human and Machine Cognition

  29 shared

• James Zou

  Stanford University

  27 shared

• Akash Srivastava

  26 shared

• Charles Sutton

  26 shared

• David Duvenaud

  21 shared

• Elaine Angelino

  20 shared

• Jasper Snoek

  20 shared

• Zoubin Ghahramani

  19 shared

Labs

• Laboratory for Intelligent Probabilistic SystemsPI

Education

• Ph.D.

  Princeton University

• M.S.

  Harvard University

• B.S.

  Harvard University

Similar researchers at Princeton University

• Jonathan Cohenh-162
• Michael Straussh-149
• Thomas E. Shenkh-136
• Michael Levineh-131
• Romain Teyssierh-130