Embed Me If You Can: A Geometric Perceptron
Solving geometric tasks involving point clouds by using machine learning is a challenging problem. Standard feed-forward neural networks combine linear or, if the bias parameter is included, affine layers and activation functions. Their geometric modeling is limited, which motivated the prior work introducing the multilayer hypersphere perceptron (MLHP). Its constituent part, i.e., the hypersphere neuron, is obtained by applying a conformal embedding of Euclidean space. By virtue of Clifford algebra, it can be implemented as the Cartesian dot product of inputs and weights. If the embedding is applied in a manner consistent with the dimensionality of the input space geometry, the decision surfaces of the model units become combinations of hyperspheres and make the decision-making process geometrically interpretable for humans. Our extension of the MLHP model, the multilayer geometric perceptron (MLGP), and its respective layer units, i.e., geometric neurons, are consistent with the 3D geometry and provide a geometric handle of the learned coefficients. In particular, the geometric neuron activations are isometric in 3D, which is necessary for rotation and translation equivariance. When classifying the 3D Tetris shapes, we quantitatively show that our model requires no activation function in the hidden layers other than the embedding to outperform the vanilla multilayer perceptron. In the presence of noise in the data, our model is also superior to the MLHP.
Code (1)
Tasks
3D geometryDecision MakingSimilar Papers 제목 키워드 기반
Polyhedrons and Perceptrons Are Functionally Equivalent
Mathematical definitions of polyhedrons and perceptron networks are discussed. The formalization of polyhedrons is done in a rather traditional way. For networks, previously proposed systems are developed. Perceptron net…
Learning from Protein Structure with Geometric Vector Perceptrons
Learning on 3D structures of large biomolecules is emerging as a distinct area in machine learning, but there has yet to emerge a unifying network architecture that simultaneously leverages the graph-structured and geome…
Protein DesignRelational ReasoningCeRF: Convolutional Neural Radiance Fields for New View Synthesis with Derivatives of Ray Modeling
In recent years, novel view synthesis has gained popularity in generating high-fidelity images. While demonstrating superior performance in the task of synthesizing novel views, the majority of these methods are still ba…
Neural RenderingNovel View SynthesisLearning Bilingual Sentence Embeddings via Autoencoding and Computing Similarities with a Multilayer Perceptron
We propose a novel model architecture and training algorithm to learn bilingual sentence embeddings from a combination of parallel and monolingual data. Our method connects autoencoding and neural machine translation to …
Machine TranslationSentenceSentence EmbeddingsTranslationEuclidean geometry meets graph, a geometric deep learning perspective
Graph neural networks (GNN) have been an active area of machine learning research to tackle various problems in graph data. Sometimes nodes and edges in a graph can have spatial features, such as 3D coordinates of nodes …
Deep LearningGraph Learning