Filters








71,829 Hits in 2.7 sec

Global shape processing involves feature-selective and feature-agnostic coding mechanisms

J. Bell, M. Forsyth, D. R. Badcock, F. A. A. Kingdom
2014 Journal of Vision  
Our findings provide evidence for two global shape mechanisms: one that is selective for shape orientation and luminance polarity, and one that is agnostic to these characteristics.  ...  Global shape processing involves feature-selective and feature-agnostic coding mechanisms.  ...  Thus the current study extends these singular examinations and by doing so, presents evidence for both feature-selective and feature-agnostic global shape mechanisms in human vision.  ... 
doi:10.1167/14.11.12 pmid:25240064 fatcat:ivom5rv2dfcgbgg3zftvdjfbca

Domain Expertise–Agnostic Feature Selection for the Analysis of Breast Cancer Data

Susanna Pozzoli, Amira Soliman, Leila Bahri, Rui Mamede Branca, Sarunas Girdzijauskas, Marco Brambilla
2020 Artificial Intelligence in Medicine  
There is a growing need for unsupervised feature selection, which raises the issue of how to generate promising subsets of features among all the possible combinations, as well as how to evaluate the quality  ...  The use of high-dimensional data has already become widespread, and a great deal of effort has been put into high-dimensional data analysis by means of feature selection, but it is still largely based  ...  The novelty of our performed work is the employment of domain knowledge-agnostic dimensionality reduction with purely unsupervised feature selection for the identification of groups of tumors that share  ... 
doi:10.1016/j.artmed.2020.101928 pmid:32972658 fatcat:4otpts65jbbj3mjzrywfdzfltq

Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Sampling [article]

Ran Tao, Han Zhang, Yutong Zheng, Marios Savvides
2022 arXiv   pre-print
Finetuning is designed to focus on reducing biases in novel-class feature distributions, which we define as two aspects: class-agnostic and class-specific biases.  ...  Class-specific bias is defined as the biased estimation using a few samples in novel classes, which we propose Selected Sampling(SS) to reduce.  ...  The first step to reduce class-agnostic bias is to calibrate skewed feature distribution.  ... 
arXiv:2204.03749v2 fatcat:is5ancke4fevpaupikxj3luqni

Explainable Software Defect Prediction: Are We There Yet? [article]

Jiho Shin, Reem Aleithan, Jaechang Nam, Junjie Wang, Song Wang
2021 arXiv   pre-print
To address this issue, recently, Jiarpakdee et al. proposed to use two state-of-the-art model-agnostic techniques (i.e., LIME and BreakDown) to explain the prediction results of bug prediction models.  ...  In this paper, we set out to investigate the consistency and reliability of model-agnostic technique based explanation generation approaches (i.e., LIME and BreakDown) on software defect prediction models  ...  In other words, only the selected features by anchor affect the final prediction.  ... 
arXiv:2111.10901v1 fatcat:qvzn4l3hprhw7mg4zljywjmgb4

Agnostic Learning versus Prior Knowledge in the Design of Kernel Machines

Gavin C. Cawley, Nicola L. C. Talbot
2007 Neural Networks (IJCNN), International Joint Conference on  
However, the degree to which the incorporation of prior knowledge improves performance over that which can be obtained using "standard" kernels with automated model selection (i.e. agnostic learning),  ...  In this paper, we compare approaches using example solutions for all of the benchmark tasks on both tracks of the IJCNN-2007 Agnostic Learning versus Prior Knowledge Challenge.  ...  -2006 model selection workshops and challenges.  ... 
doi:10.1109/ijcnn.2007.4371219 dblp:conf/ijcnn/CawleyT07 fatcat:s4liwsmdenahfazexe3smzxude

Agnostic Learning vs. Prior Knowledge Challenge

Isabelle Guyon, Amir Saffari, Gideon Dror, Gavin Cawley
2007 Neural Networks (IJCNN), International Joint Conference on  
participants were allowed to compete in two tracks: The "prior knowledge" track, for which they had access to the original raw data representation and as much knowledge as possible about the data, and the "agnostic  ...  learning" track for which they were forced to use data pre-formatted as a table with dummy features.  ...  data normalization or feature selection).  ... 
doi:10.1109/ijcnn.2007.4371065 dblp:conf/ijcnn/GuyonSDC07 fatcat:zkbv4eyq7rbibm337jznoir57i

Question-Agnostic Attention for Visual Question Answering [article]

Moshiur R Farazi, Salman H Khan, Nick Barnes
2020 arXiv   pre-print
The resulting multimodal representations define an intermediate feature space for capturing the interplay between visual and semantic features, that is helpful in selectively focusing on image content.  ...  Our proposed model parses object instances to obtain an 'object map' and applies this map on the visual features to generate Question-Agnostic Attention (QAA) features.  ...  Most importantly, the multimodal embedding is used to selectively attend to visual features using a learned attention mechanism.  ... 
arXiv:1908.03289v2 fatcat:g7oq7tmipfbt5jyxwheiq2wel4

Predicting Quitting in Students Playing a Learning Game

Shamya Karumbaiah, Ryan S. Baker, Valerie J. Shute
2018 Educational Data Mining  
From the interaction log data of the game, we engineered a comprehensive set of aggregated features of varying levels of granularity and trained individualized level-specific models and a single level-agnostic  ...  Contrary to our initial expectation, our results suggest that a level-agnostic model achieves superior predictive performance.  ...  (Figure 5H; studentrelated feature) 9. Table 2 . Comparing top features selected in level-agnostic and level-specific models. Selected Feature In level- agnostic model?  ... 
dblp:conf/edm/KarumbaiahBS18 fatcat:vncptisb6nfgldpz7mkbxstbee

GLIME: A new graphical methodology for interpretable model-agnostic explanations [article]

Zoumpolia Dikopoulou, Serafeim Moustakidis, Patrik Karlsson
2021 arXiv   pre-print
It relies on a combination of local interpretable model-agnostic explanations (LIME) with graphical least absolute shrinkage and selection operator (GLASSO) producing undirected Gaussian graphical models  ...  The proposed XAI methodology, termed as gLIME, provides graphical model-agnostic explanations either at the global (for the entire dataset) or the local scale (for specific data points).  ...  It relies on a combination of local interpretable model-agnostic explanations (LIME) with graphical least absolute shrinkage and selection operator (GLASSO) Epskamp and Fried [2018] , Meinshausen et  ... 
arXiv:2107.09927v1 fatcat:z2uz6s26z5ecjhxtcgo2rdr3me

Interpreting search result rankings through intent modeling [article]

Jaspreet Singh, Avishek Anand
2018 arXiv   pre-print
Given the recent interest in arguably accurate yet non-interpretable neural models, even with textual features, for document ranking we try to answer questions relating to how to interpret rankings.  ...  In fact, we consider two levels of model-agnostic interpretability weak agnosticism and strong agnosticism.  ...  Weak and Strong Model Agnosticism: In this paper we specifically consider a post-hoc model agnostic setting to understand ranking decisions.  ... 
arXiv:1809.05190v1 fatcat:bph6psznpjdjvmhu2236hphloy

Designing WiMAX Static Environment using Local Automata based Autonomic Network Architecture for Wireless Sensor Networks

Sanjay K N, Shaila K, Venugopal K R
2021 Procedia Computer Science  
Advanced with static environment configuring address agnostic feature could bridge the gap between static and dynamic environments.  ...  Advanced with static environment configuring address agnostic feature could bridge the gap between static and dynamic environments.  ...  Thus, avoiding congestion by selecting neighborhood in case of node failure. Further, address agnostic feature at WiMAX station helps in reducing dark spots of station.  ... 
doi:10.1016/j.procs.2021.04.017 fatcat:cdcfe52qrfcitlasej6sc4ug3y

linc2function: A deep learning model to identify and assign function to long noncoding RNA (lncRNA) [article]

Yashpal Ramakrishnaiah, Levin Kuhlmann, Sonika Tyagi
2021 bioRxiv   pre-print
Additionally, effective models will have to provide maximum prediction performance using the least number of features in a species-agnostic manner.  ...  Based on our analysis, we built different machine learning models using optimum feature-set.  ...  Feature Selection In the first step, we eliminated the features using co-variance analysis, univariate feature selection techniques [35] , and by feature importance measures using forests of trees.  ... 
doi:10.1101/2021.01.29.428785 fatcat:sfgkwaj3yfes7kq7srbzbgahlm

Starting Movement Detection of Cyclists Using Smart Devices [article]

Maarten Bieshaar, Malte Depping, Jan Schneegans, Bernhard Sick
2018 arXiv   pre-print
We propose a novel two-stage feature selection procedure using a score specialized for robust starting detection reducing the false positive detections and leading to understandable and interpretable features  ...  . • A two-stage feature selection procedure to select robust features.  ...  , we apply backward feature selection.  ... 
arXiv:1808.04449v1 fatcat:mhzdncmra5dwzeqvm5epmxsntm

Class-agnostic Object Detection with Multi-modal Transformer [article]

Muhammad Maaz, Hanoona Rasheed, Salman Khan, Fahad Shahbaz Khan, Rao Muhammad Anwer, Ming-Hsuan Yang
2022 arXiv   pre-print
Based on the observation that existing MViTs do not include multi-scale feature processing and usually require longer training schedules, we develop an efficient MViT architecture using multi-scale deformable  ...  Class-agnostic OD of DETReg [3] when trained using Selective Search (SS) [64] versus MAVL proposals (bottom).  ...  Fig. 9 : Class-agnostic OD performance of DETReg [3] trained using Selective Search [64] versus MAVL proposals.  ... 
arXiv:2111.11430v6 fatcat:q6xf7mdrmzcaji7qytav7xkpta

Model-Agnostic Interpretability of Machine Learning [article]

Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin
2016 arXiv   pre-print
Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to trust and act upon the predictions  ...  In this paper we argue for explaining machine learning predictions using model-agnostic approaches.  ...  Challenges for Model-agnostic Explanations While we have made a case for model agnosticism, this approach is not without its challenges.  ... 
arXiv:1606.05386v1 fatcat:ayelsgzb5rf4dme5v3osls6dim
« Previous Showing results 1 — 15 out of 71,829 results