Predictive coding approximates backprop along arbitrary computation graphs

B Millidge, A Tschantz, CL Buckley - Neural Computation, 2022 - direct.mit.edu
Backpropagation of error (backprop) is a powerful algorithm for training machine learning
architectures through end-to-end differentiation. Recently it has been shown that backprop …

Automatic heliostat learning for in situ concentrating solar power plant metrology with differentiable ray tracing

M Pargmann, J Ebert, M Götz… - Nature …, 2024 - nature.com
Concentrating solar power plants are a clean energy source capable of competitive
electricity generation even during night time, as well as the production of carbon-neutral …

[图书][B] Response Surface Modeling Vehicle Subframe Compliance Optimization Framework and Structural Topology Optimization through Differentiable Physics …

L Chen - 2021 - search.proquest.com
Sizing and topology optimization are the two main structural optimization tools in a wide
range of applications in aerospace, mechanical, and design. An iterative process solves the …

[PDF][PDF] A Julia Implementation of the Differentiable Neural Computer

SJE Rodahl - 2020 - ntnuopen.ntnu.no
In the paradigm of differentiable programming, programs are modeled as a parameterized
solution prototype, which is trained by gradient-based optimization. DeepMind's Differential …