Výsledky vyhledávání - "Ibraheem, Abdulrahman"

Report

T- Hop: A framework for studying the importance path information in molecular graphs for chemical property prediction

Autor: Ibraheem, Abdulrahman, Kiani, Narsis, Tegner, Jesper

This paper studies the usefulness of incorporating path information in predicting chemical properties from molecular graphs, in the domain of QSAR (Quantitative Structure-Activity Relationship). Towards this, we developed a GNN-style model which can

Externí odkaz: http://arxiv.org/abs/2407.14270

Zobrazit plný text záznamu

Report

T- Hop: Tensor representation of paths in graph convolutional networks

Autor: Ibraheem, Abdulrahman

We describe a method for encoding path information in graphs into a 3-d tensor. We show a connection between the introduced path representation scheme and powered adjacency matrices. To alleviate the heavy computational demands of working with the 3-

Externí odkaz: http://arxiv.org/abs/2204.04983

Zobrazit plný text záznamu

Report

HBert + BiasCorp -- Fighting Racism on the Web

Autor: Onabola, Olawale, Ma, Zhuang, Xie, Yang, Akera, Benjamin, Ibraheem, Abdulrahman, Xue, Jia, Liu, Dianbo, Bengio, Yoshua

Publikováno v: ltedi-1. 4 (2021) 26-33

Subtle and overt racism is still present both in physical and online communities today and has impacted many lives in different segments of the society. In this short piece of work, we present how we're tackling this societal issue with Natural Langu

Externí odkaz: http://arxiv.org/abs/2104.02242

Zobrazit plný text záznamu

Report

Compact Shape Trees: A Contribution to the Forest of Shape Correspondences and Matching Methods

Autor: Ibraheem, Abdulrahman Oladipupo

We propose a novel technique, termed compact shape trees, for computing correspondences of single-boundary 2-D shapes in O(n2) time. Together with zero or more features defined at each of n sample points on the shape's boundary, the compact shape tre

Externí odkaz: http://arxiv.org/abs/1506.02923

Zobrazit plný text záznamu

Report

Bi-directional Shape Correspondences (BSC): A Novel Technique for 2-d Shape Warping in Quadratic Time?

Autor: Ibraheem, Abdulrahman Oladipupo

We propose Bidirectional Shape Correspondence (BSC) as a possible improvement on the famous shape contexts (SC) framework. Our proposals derive from the observation that the SC framework enforces a one-to-one correspondence between sample points, and

Externí odkaz: http://arxiv.org/abs/1412.6759

Zobrazit plný text záznamu

Report

SENNS: Sparse Extraction Neural NetworkS for Feature Extraction

Autor: Ibraheem, Abdulrahman Oladipupo

By drawing on ideas from optimisation theory, artificial neural networks (ANN), graph embeddings and sparse representations, I develop a novel technique, termed SENNS (Sparse Extraction Neural NetworkS), aimed at addressing the feature extraction pro

Externí odkaz: http://arxiv.org/abs/1412.6749

Zobrazit plný text záznamu

Report

Correlation of Data Reconstruction Error and Shrinkages in Pair-wise Distances under Principal Component Analysis (PCA)

Autor: Ibraheem, Abdulrahman Oladipupo

In this on-going work, I explore certain theoretical and empirical implications of data transformations under the PCA. In particular, I state and prove three theorems about PCA, which I paraphrase as follows: 1). PCA without discarding eigenvector ro

Externí odkaz: http://arxiv.org/abs/1412.6752

Zobrazit plný text záznamu