Výsledky vyhledávání - "BAIN, Michael"

Report

Retina Vision Transformer (RetinaViT): Introducing Scaled Patches into Vision Transformers

Humans see low and high spatial frequency components at the same time, and combine the information from both to form a visual scene. Drawing on this neuroscientific inspiration, we propose an altered Vision Transformer architecture where patches from

Externí odkaz: http://arxiv.org/abs/2403.13677

Zobrazit plný text záznamu

Report

A Model for Intelligible Interaction Between Agents That Predict and Explain

Autor: Baskar, A., Srinivasan, Ashwin, Bain, Michael, Coiera, Enrico

Machine Learning (ML) has emerged as a powerful form of data modelling with widespread applicability beyond its roots in the design of autonomous agents. However, relatively little attention has been paid to the interaction between people and ML syst

Externí odkaz: http://arxiv.org/abs/2301.01819

Zobrazit plný text záznamu

Report

One-way Explainability Isn't The Message

Autor: Srinivasan, Ashwin, Bain, Michael, Coiera, Enrico

Recent engineering developments in specialised computational hardware, data-acquisition and storage technology have seen the emergence of Machine Learning (ML) as a powerful form of data analysis with widespread applicability beyond its historical ro

Externí odkaz: http://arxiv.org/abs/2205.08954

Zobrazit plný text záznamu

Report

Logical Explanations for Deep Relational Machines Using Relevance Information

Autor: Srinivasan, Ashwin, Vig, Lovekesh, Bain, Michael

Our interest in this paper is in the construction of symbolic explanations for predictions made by a deep neural network. We will focus attention on deep relational machines (DRMs, first proposed by H. Lodhi). A DRM is a deep network in which the inp

Externí odkaz: http://arxiv.org/abs/1807.00595

Zobrazit plný text záznamu

Report

B-CNN: Branch Convolutional Neural Network for Hierarchical Classification

Autor: Zhu, Xinqi, Bain, Michael

Convolutional Neural Network (CNN) image classifiers are traditionally designed to have sequential convolutional layers with a single output layer. This is based on the assumption that all target classes should be treated equally and exclusively. How

Externí odkaz: http://arxiv.org/abs/1709.09890

Zobrazit plný text záznamu

Report

Word Vector Enrichment of Low Frequency Words in the Bag-of-Words Model for Short Text Multi-class Classification Problems

Autor: Heap, Bradford, Bain, Michael, Wobcke, Wayne, Krzywicki, Alfred, Schmeidl, Susanne

The bag-of-words model is a standard representation of text for many linear classifier learners. In many problem domains, linear classifiers are preferred over more complex models due to their efficiency, robustness and interpretability, and the bag-

Externí odkaz: http://arxiv.org/abs/1709.05778

Zobrazit plný text záznamu