Search Results for author: Isaac Tamblyn

Found 29 papers, 9 papers with code

Dynamic Observation Policies in Observation Cost-Sensitive Reinforcement Learning

1 code implementation5 Jul 2023 Colin Bellinger, Mark Crowley, Isaac Tamblyn

The action-perception cycle in RL, however, generally assumes that a measurement of the state of the environment is available at each time step without a cost.

OpenAI Gym reinforcement-learning +2

fintech-kMC: Agent based simulations of financial platforms for design and testing of machine learning systems

no code implementations4 Jan 2023 Isaac Tamblyn, Tengkai Yu, Ian Benlolo

We discuss our simulation tool, fintech-kMC, which is designed to generate synthetic data for machine learning model development and testing.

Training neural networks using Metropolis Monte Carlo and an adaptive variant

1 code implementation16 May 2022 Stephen Whitelam, Viktor Selin, Ian Benlolo, Corneel Casert, Isaac Tamblyn

We examine the zero-temperature Metropolis Monte Carlo algorithm as a tool for training a neural network by minimizing a loss function.

Machine Learning Diffusion Monte Carlo Energies

no code implementations9 May 2022 Kevin Ryczko, Jaron T. Krogel, Isaac Tamblyn

We present two machine learning methodologies that are capable of predicting diffusion Monte Carlo (DMC) energies with small datasets (~60 DMC calculations in total).

BIG-bench Machine Learning regression +1

Generative Enriched Sequential Learning (ESL) Approach for Molecular Design via Augmented Domain Knowledge

no code implementations5 Apr 2022 Mohammad Sajjad Ghaemi, Karl Grantham, Isaac Tamblyn, Yifeng Li, Hsu Kiang Ooi

Deploying generative machine learning techniques to generate novel chemical structures based on molecular fingerprint representation has been well established in molecular design.

Cellular automata can classify data by inducing trajectory phase coexistence

no code implementations10 Mar 2022 Stephen Whitelam, Isaac Tamblyn

We show that cellular automata can classify data by inducing a form of dynamical phase coexistence.

Learning stochastic dynamics and predicting emergent behavior using transformers

1 code implementation17 Feb 2022 Corneel Casert, Isaac Tamblyn, Stephen Whitelam

We show that a neural network originally designed for language processing can learn the dynamical rules of a stochastic system by observation of a single dynamical trajectory of the system, and can accurately predict its emergent behavior under conditions not observed during training.

Dynamic programming with incomplete information to overcome navigational uncertainty in a nautical environment

no code implementations29 Dec 2021 Chris Beeler, Xinkai Li, Colin Bellinger, Mark Crowley, Maia Fraser, Isaac Tamblyn

Using a novel toy nautical navigation environment, we show that dynamic programming can be used when only incomplete information about a partially observed Markov decision process (POMDP) is known.

Scientific Discovery and the Cost of Measurement -- Balancing Information and Cost in Reinforcement Learning

no code implementations14 Dec 2021 Colin Bellinger, Andriy Drozdyuk, Mark Crowley, Isaac Tamblyn

The use of reinforcement learning (RL) in scientific applications, such as materials design and automated chemistry, is increasing.

Reinforcement Learning (RL)

Twin Neural Network Regression is a Semi-Supervised Regression Algorithm

no code implementations11 Jun 2021 Sebastian J. Wetzel, Roger G. Melko, Isaac Tamblyn

Twin neural network regression (TNNR) is a semi-supervised regression algorithm, it can be trained on unlabelled data points as long as other, labelled anchor data points, are present.


Unsupervised Hyperspectral Stimulated Raman Microscopy Image Enhancement: Denoising and Segmentation via One-Shot Deep Learning

1 code implementation14 Apr 2021 Pedram Abdolghader, Andrew Ridsdale, Tassos Grammatikopoulos, Gavin Resch, Francois Legare, Albert Stolow, Adrian F. Pegoraro, Isaac Tamblyn

Hyperspectral stimulated Raman scattering (SRS) microscopy is a label-free technique for biomedical and mineralogical imaging which can suffer from low signal to noise ratios.

Clustering Denoising +5

Golem: An algorithm for robust experiment and process optimization

1 code implementation5 Mar 2021 Matteo Aldeghi, Florian Häse, Riley J. Hickman, Isaac Tamblyn, Alán Aspuru-Guzik

Design of experiment and optimization algorithms are often adopted to solve these tasks efficiently.

Weakly-supervised multi-class object localization using only object counts as labels

no code implementations23 Feb 2021 Kyle Mills, Isaac Tamblyn

Using images labelled with only the counts of the objects present, the structure of the extensive deep neural network can be exploited to perform localization of the objects within the visual field.

Object Object Localization

Interpretable discovery of new semiconductors with machine learning

no code implementations12 Jan 2021 Hitarth Choubisa, Petar Todorović, Joao M. Pina, Darshan H. Parmar, Ziliang Li, Oleksandr Voznyy, Isaac Tamblyn, Edward Sargent

To provide guidance in experimental materials synthesis, these need to be coupled with an accurate yet effective search algorithm and training data consistent with experimental observations.

BIG-bench Machine Learning Knowledge Distillation

Twin Neural Network Regression

no code implementations29 Dec 2020 Sebastian J. Wetzel, Kevin Ryczko, Roger G. Melko, Isaac Tamblyn

The solution of a traditional regression problem is then obtained by averaging over an ensemble of all predicted differences between the targets of an unseen data point and all training data points.


Neuroevolutionary learning of particles and protocols for self-assembly

no code implementations22 Dec 2020 Stephen Whitelam, Isaac Tamblyn

Within simulations of molecules deposited on a surface we show that neuroevolutionary learning can design particles and time-dependent protocols to promote self-assembly, without input from physical concepts such as thermal equilibrium or mechanical stability and without prior knowledge of candidate or competing structures.

Dynamical large deviations of two-dimensional kinetically constrained models using a neural-network state ansatz

no code implementations17 Nov 2020 Corneel Casert, Tom Vieijra, Stephen Whitelam, Isaac Tamblyn

We use a neural network ansatz originally designed for the variational optimization of quantum systems to study dynamical large deviations in classical ones.

Scientific intuition inspired by machine learning generated hypotheses

no code implementations27 Oct 2020 Pascal Friederich, Mario Krenn, Isaac Tamblyn, Alan Aspuru-Guzik

Machine learning with application to questions in the physical sciences has become a widely used tool, successfully applied to classification, regression and optimization tasks in many areas.

BIG-bench Machine Learning

Correspondence between neuroevolution and gradient descent

no code implementations15 Aug 2020 Stephen Whitelam, Viktor Selin, Sang-Won Park, Isaac Tamblyn

We show analytically that training a neural network by conditioned stochastic mutation or neuroevolution of its weights is equivalent, in the limit of small mutations, to gradient descent on the loss function in the presence of Gaussian white noise.

Active Measure Reinforcement Learning for Observation Cost Minimization

no code implementations26 May 2020 Colin Bellinger, Rory Coles, Mark Crowley, Isaac Tamblyn

Our empirical evaluation demonstrates that Amrl-Q agents are able to learn a policy and state estimator in parallel during online training.

Decision Making Q-Learning +2

Reinforcement Learning in a Physics-Inspired Semi-Markov Environment

1 code implementation15 Apr 2020 Colin Bellinger, Rory Coles, Mark Crowley, Isaac Tamblyn

Reinforcement learning (RL) has been demonstrated to have great potential in many applications of scientific discovery and design.

reinforcement-learning Reinforcement Learning (RL)

Watch and learn -- a generalized approach for transferrable learning in deep neural networks via physical principles

1 code implementation3 Mar 2020 Kyle Sprague, Juan Carrasquilla, Steve Whitelam, Isaac Tamblyn

Transfer learning refers to the use of knowledge gained while solving a machine learning task and applying it to the solution of a closely related problem.

Transfer Learning

Learning to grow: control of material self-assembly using evolutionary reinforcement learning

no code implementations18 Dec 2019 Stephen Whitelam, Isaac Tamblyn

We show that neural networks trained by evolutionary reinforcement learning can enact efficient molecular self-assembly protocols.

reinforcement-learning Reinforcement Learning (RL)

Evolutionary reinforcement learning of dynamical large deviations

no code implementations2 Sep 2019 Stephen Whitelam, Daniel Jacobson, Isaac Tamblyn

We show how to calculate the likelihood of dynamical large deviations using evolutionary reinforcement learning.

reinforcement-learning Reinforcement Learning (RL)

Phase space sampling and operator confidence with generative adversarial networks

no code implementations23 Oct 2017 Kyle Mills, Isaac Tamblyn

We demonstrate that a generative adversarial network can be trained to produce Ising model configurations in distinct regions of phase space.

Statistical Mechanics

Extensive deep neural networks for transferring small scale learning to large scale systems

no code implementations17 Aug 2017 Kyle Mills, Kevin Ryczko, Iryna Luchak, Adam Domurad, Chris Beeler, Isaac Tamblyn

We demonstrate the application of EDNNs to three physical systems: the Ising model and two hexagonal/graphene-like datasets.

Computational Physics Materials Science

Deep learning and the Schrödinger equation

1 code implementation5 Feb 2017 Kyle Mills, Michael Spanner, Isaac Tamblyn

We have trained a deep (convolutional) neural network to predict the ground-state energy of an electron in four classes of confining two-dimensional electrostatic potentials.

Cannot find the paper you are looking for? You can Submit a new open access paper.