paper-with-me

Papers

Energy Optimized Piecewise Polynomial Approximation Utilizing Modern Machine Learning Optimizers

2025-03-12 · Hannes Waclawek, Stefan Huber

This work explores an extension of ML-optimized piecewise polynomial approximation by incorporating energy optimization as an additional objective. Traditional closed-form solutions enable continuity and approximation targets but lack flexibility in accommodating complex optimization goals. By leveraging modern gradient descent optimizers within TensorFlow, we introduce a framework that minimizes total curvature in cam profiles, leading to smoother motion and reduced energy consumption for input data that is unfavorable for sole approximation and continuity optimization. Experimental results confirm the effectiveness of this approach, demonstrating its potential to improve efficiency in scenarios where input data is noisy or suboptimal for conventional methods.

📄 PDF Abstract BibTeX arXiv:2503.09329

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

CAM Class activation maps could be used to interpret the prediction decision made by the convolutional neural network (CNN). Image source: [Learning Deep Features for…

Similar Papers 제목 키워드 기반

Machine Learning Optimized Orthogonal Basis Piecewise Polynomial Approximation

2024-03-13 · Hannes Waclawek, Stefan Huber

Piecewise Polynomials (PPs) are utilized in several engineering disciplines, like trajectory planning, to approximate position profiles given in the form of a set of points. While the approximation target along with doma…

Trajectory Planning

Constructing Multilayer Perceptrons as Piecewise Low-Order Polynomial Approximators: A Signal Processing Approach

2020-10-15 · Ruiyuan Lin, Suya You, Raghuveer Rao, C. -C. Jay Kuo

The construction of a multilayer perceptron (MLP) as a piecewise low-order polynomial approximator using a signal processing approach is presented in this work. The constructed MLP contains one input, one intermediate an…

Piecewise Polynomial Regression of Tame Functions via Integer Programming

2023-11-22 · Gilles Bareilles, Johannes Aspman, Jiri Nemecek, Jakub Marecek

Tame functions are a class of nonsmooth, nonconvex functions, which feature in a wide range of applications: functions encountered in the training of deep neural networks with all common activations, value functions of m…

regression

Partition of unity networks: deep hp-approximation

2021-01-27 · Kookjin Lee, Nathaniel A. Trask, Ravi G. Patel, Mamikon A. Gulian 외

Approximation theorists have established best-in-class optimal approximation rates of deep neural networks by utilizing their ability to simultaneously emulate partitions of unity and monomials. Motivated by this, we pro…

Unity

Optimized Piecewise Affine Abstractions of Neural Networks with Learnable Activation Functions

2026-02-06 · Noah Schwartz, Chandra Kanth Nagesh, Sriram Sankaranarayanan, Ramneet Kaur 외 arxiv

We present a generalized framework for the range verification of neural networks featuring non-linear activation functions. Our approach first constructs an ``optimized piecewise affine abstraction" of the network that r…

Gaussian Processes