Search Results for author:
Found 3 papers, 0 papers with code
Ultimate limit on learning non-Markovian behavior: Fisher information rate and excess information
We address the fundamental limits of learning unknown parameters of any stochastic process from time-series data, and discover exact closed-form expressions for how optimal inference scales with observation length.
Complexity-calibrated Benchmarks for Machine Learning Reveal When Next-Generation Reservoir Computer Predictions Succeed and Mislead
One conclusion is that large probabilistic state machines -- specifically, large $\epsilon$-machines -- are key to generating challenging and structurally-unbiased stimuli for ground-truthing recurrent neural network architectures.
Transforming Metastable Memories: The Nonequilibrium Thermodynamics of Computation
Framing computation as the transformation of metastable memories, we explore its fundamental thermodynamic limits.
Statistical Mechanics Applied Physics 80-02, 82C03, 82C05, 68Q10 F.0
