Search Results for author:
Found 6 papers, 1 papers with code
Thermodynamic Machine Learning through Maximum Work Production
We introduce the thermodynamic principle that work production is the most relevant performance metric for an adaptive physical agent and compare the results to the maximum-likelihood principle that guides machine learning.
Inference, Prediction, and Entropy-Rate Estimation of Continuous-time, Discrete-event Processes
Inferring models, predicting the future, and estimating the entropy rate of discrete-time, discrete-event processes is well-worn ground.
Probabilistic Deterministic Finite Automata and Recurrent Networks, Revisited
Reservoir computers (RCs) and recurrent neural networks (RNNs) can mimic any finite-state automaton in theory, and some workers demonstrated that this can hold in practice.
Optimizing Quantum Models of Classical Channels: The reverse Holevo problem
Given a classical channel---a stochastic map from inputs to outputs---the input can often be transformed to an intermediate variable that is informationally smaller than the input.
Identifying Functional Thermodynamics in Autonomous Maxwellian Ratchets
We introduce a family of Maxwellian Demons for which correlations among information bearing degrees of freedom can be calculated exactly and in compact analytical form.
Statistical Mechanics Dynamical Systems Chaotic Dynamics Biological Physics Chemical Physics
Pairwise Correlations in Layered Close-Packed Structures
Given a description of the stacking statistics of layered close-packed structures in the form of a hidden Markov model, we develop analytical expressions for the pairwise correlation functions between the layers.
