Differentiable Genetic Programming

Izzo, Dario; Biscani, Francesco; Mereta, Alessio

doi:10.48550/arxiv.1611.04766

Cited by 2 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While probabilistic programming facilitates generic computations involving probability distributions, differentiable programming ( Izzo et al., 2016 ; Innes et al., 2019 ) extends computation by enabling differentiation of arbitrary computer programs ( Figure 1G ). This empowers the fine-tuning of program behavior using gradient-based optimization techniques.…”

Section: Nine Simulation Intelligence Motifs For Plant Sciencementioning

confidence: 99%

Plant science in the age of simulation intelligence

Stock,

Pieters,

De Swaef

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

Historically, plant and crop sciences have been quantitative fields that intensively use measurements and modeling. Traditionally, researchers choose between two dominant modeling approaches: mechanistic plant growth models or data-driven, statistical methodologies. At the intersection of both paradigms, a novel approach referred to as “simulation intelligence”, has emerged as a powerful tool for comprehending and controlling complex systems, including plants and crops. This work explores the transformative potential for the plant science community of the nine simulation intelligence motifs, from understanding molecular plant processes to optimizing greenhouse control. Many of these concepts, such as surrogate models and agent-based modeling, have gained prominence in plant and crop sciences. In contrast, some motifs, such as open-ended optimization or program synthesis, still need to be explored further. The motifs of simulation intelligence can potentially revolutionize breeding and precision farming towards more sustainable food production.

show abstract

Section: Nine Simulation Intelligence Motifs For Plant Sciencementioning

confidence: 99%

Plant science in the age of simulation intelligence

Stock,

Pieters,

De Swaef

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

Section: Algorithmmentioning

confidence: 99%

“…We can now use symbolic regression [30,31] to automatically build a mathematical expression q sr (x, y) that approximately reproduces the machine learned optimal RC qopt ANN (x|w). Symbolic regression finds the best fit to a given data set searching both model and parameter space by genetic programming, evolving combinations of elementary functions and input variables through random mutations and survival of the fittest [31]. Applied to our model system with input variables (x, y), symbolic regression produces a simplified RC, q sr (x, y) = (3.32x + 1.24y) exp (2.92xy), which corresponds to a committor in excellent agreement with the exact one (Figure 3).…”

Section: Algorithmmentioning

confidence: 99%

“…The implementation of the symbolic regression is based on the python package dcgpy [31], and alternates between genetic programming optimization and gradient based optimization of the constants. The fitness of each trial expression q sr (z) is measured by l sr (q sr |θ) ≡ − log L tot [q sr (z sp )] + λn c , where z is a subset of all input coordinates x.…”

Section: Symbolic Regressionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence Assists Discovery of Reaction Coordinates and Mechanisms from Molecular Dynamics Simulations

Jung,

Covino,

Hummer

2019

Preprint

View full text Add to dashboard Cite

Exascale computing holds great opportunities for molecular dynamics (MD) simulations. However, to take full advantage of the new possibilities, we must learn how to focus computational power on the discovery of complex molecular mechanisms, and how to extract them from enormous amounts of data. Both aspects still rely heavily on human experts, which becomes a serious bottleneck when a large number of parallel simulations have to be orchestrated to take full advantage of the available computing power. Here, we use artificial intelligence (AI) both to guide the sampling and to extract the relevant mechanistic information. We combine advanced sampling schemes with statistical inference, artificial neural networks, and deep learning to discover molecular mechanisms from MD simulations. Our framework adaptively and autonomously initializes simulations and learns the sampled mechanism, and is thus suitable for massively parallel computing architectures. We propose practical solutions to make the neural networks interpretable, as illustrated in applications to molecular systems.

show abstract

Differentiable Genetic Programming

Cited by 2 publications

References 0 publications

Plant science in the age of simulation intelligence

Plant science in the age of simulation intelligence

Artificial Intelligence Assists Discovery of Reaction Coordinates and Mechanisms from Molecular Dynamics Simulations

Contact Info

Product

Resources

About