Vector Field Based Neural Networks
A novel Neural Network architecture is proposed using the mathematically and physically rich idea of vector fields as hidden layers to perform nonlinear transformations in the data. The data points are interpreted as particles moving along a flow defined by the vector field which intuitively represents the desired movement to enable classification. The architecture moves the data points from their original configuration to anew one following the streamlines of the vector field with the objective of achieving a final configuration where classes are separable. An optimization problem is solved through gradient descent to learn this vector field.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationSimilar Papers 제목 키워드 기반
Non-singular Cooperative Guiding Vector Field Under a Homotopy Equivalence Transformation
The present article advances the concept of a non-singular cooperative guiding vector field under a homotopy equivalence transformation. Firstly, the derivation of a guiding vector field, based on a non-singular vector f…
NavigateLearning Stable Vector Fields on Lie Groups
Learning robot motions from demonstration requires models able to specify vector fields for the full robot pose when the task is defined in operational space. Recent advances in reactive motion generation have shown that…
Motion GenerationMulti-task Vector Field Learning
Multi-task learning (MTL) aims to improve generalization performance by learning multiple related tasks simultaneously and identifying the shared information among tasks. Most of existing MTL methods focus on learning li…
Multi-Task LearningComparing vector fields across surfaces: interest for characterizing the orientations of cortical folds
Vectors fields defined on surfaces constitute relevant and useful representations but are rarely used. One reason might be that comparing vector fields across two surfaces of the same genus is not trivial: it requires to…
Overcoming the ill-posedness through discretization in vector tomography: Reconstruction of irrotational vector fields
Vector tomography methods intend to reconstruct and visualize vector fields in restricted domains by measuring line integrals of projections of these vector fields. Here, we deal with the reconstruction of irrotational v…