Gerald Friedland
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Gerald Friedland has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Jaeyoung Choi
International Computer Science Institute
7 shared publications - Howard Lei
International Computer Science Institute
2 shared publications - Kannan Ramchandran
University of California, Berkeley
2 shared publications - Luke Gottlieb
International Computer Science Institute
2 shared publications - Pascal Kelm
Technische Universität
2 shared publications - Venkatesan Ekambaram
University of California
2 shared publications
Latest Publications
- Open Access
Effects of Feature Correlations on Associative Memory Capacity
We investigate how feature correlations influence the capacity of Dense Associative Memory (DAM), a Transformer attention-like model. Practical machine learning scenarios involve feature-correlated data and learn representations in the input space, but current capacity analyses do not account for this. We develop an empirical framework to analyze the effects of data structure on capacity dynamics. Specifically, we systematically construct datasets that vary in feature correlation and pattern separation using Hamming distance from information theory, and compute the model's corresponding storage capacity using a simple binary search algorithm. Our experiments confirm that memory capacity scales exponentially with increasing separation in the input space. Feature correlations do not alter this relationship fundamentally, but reduce capacity slightly at constant separation. This effect is amplified at higher polynomial degrees in the energy function, suggesting that Associative Memory is more limited in depicting higher-order interactions between features than patterns. Our findings bridge theoretical work and practical settings for DAM, and might inspire more data-centric methods.
Open AccessEffects of Feature Correlations on Associative Memory Capacity
We investigate how feature correlations influence the capacity of Dense Associative Memory (DAM), a Transformer attention-like model. Practical machine learning scenarios involve feature-correlated data and learn representations in the input space, but current capacity analyses do not account for this. We develop an empirical framework to analyze the effects of data structure on capacity dynamics. Specifically, we systematically construct datasets that vary in feature correlation and pattern separation using Hamming distance from information theory, and compute the model's corresponding storage capacity using a simple binary search algorithm. Our experiments confirm that memory capacity scales exponentially with increasing separation in the input space. Feature correlations do not alter this relationship fundamentally, but reduce capacity slightly at constant separation. This effect is amplified at higher polynomial degrees in the energy function, suggesting that Associative Memory is more limited in depicting higher-order interactions between features than patterns. Our findings bridge theoretical work and practical settings for DAM, and might inspire more data-centric methods.
- 1 April 2015
- Published by Springer Nature
- p. 157-173
Content-Based Privacy for Consumer-Produced Multimedia
- 1 April 2015
- Published by Springer Nature
- p. 157-173
Content-Based Privacy for Consumer-Produced Multimedia
- 5 October 2014
- Published by Springer Nature
- p. 153-171
Human Versus Machine: Establishing a Human Baseline for Multimodal Location Estimation
- 5 October 2014
- Published by Springer Nature
- p. 153-171
Human Versus Machine: Establishing a Human Baseline for Multimodal Location Estimation
- 5 October 2014
- Published by Springer Nature
- p. 115-126
Collaborative Multimodal Location Estimation of Consumer Media
- 5 October 2014
- Published by Springer Nature
- p. 115-126
Collaborative Multimodal Location Estimation of Consumer Media
- 5 October 2014
- Published by Springer Nature
- p. 101-113
Application of Large-Scale Classification Techniques for Simple Location Estimation Experiments
- 5 October 2014
- Published by Springer Nature
- p. 101-113
Application of Large-Scale Classification Techniques for Simple Location Estimation Experiments
- 5 October 2014
- Published by Springer Nature
- p. 5-40
The Benchmark as a Research Catalyst: Charting the Progress of Geo-prediction for Social Multimedia
- 5 October 2014
- Published by Springer Nature
- p. 5-40
The Benchmark as a Research Catalyst: Charting the Progress of Geo-prediction for Social Multimedia
- 5 October 2014
- Published by Springer Nature
- p. 1-4
Introduction
- 12 August 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 16 (15209210) , 1
Creating experts from the crowd: Techniques for finding workers for difficult tasks
Crowdsourcing is currently used for a range of applications, either by exploiting unsolicited user-generated content, such as spontaneously annotated images, or by utilizing explicit crowdsourcing platforms such as Amazon Mechanical Turk to mass-outsource artificial-intelligence-type jobs. However, crowdsourcing is most often seen as the best option for tasks that do not require more of people than their uneducated intuition as a human being. This article describes our methods for identifying workers for crowdsourced tasks that are difficult for both machines and humans. It discusses the challenges we encountered in qualifying annotators and the steps we took to select the individuals most likely to do well at these tasks.
- 12 August 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 16 (15209210) , 1
Creating experts from the crowd: Techniques for finding workers for difficult tasks
Crowdsourcing is currently used for a range of applications, either by exploiting unsolicited user-generated content, such as spontaneously annotated images, or by utilizing explicit crowdsourcing platforms such as Amazon Mechanical Turk to mass-outsource artificial-intelligence-type jobs. However, crowdsourcing is most often seen as the best option for tasks that do not require more of people than their uneducated intuition as a human being. This article describes our methods for identifying workers for crowdsourced tasks that are difficult for both machines and humans. It discusses the challenges we encountered in qualifying annotators and the steps we took to select the individuals most likely to do well at these tasks.