Výsledky vyhledávání - "RICHARDS, LUKE"

Report

Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognition

Autor: Richards, Luke E., Raff, Edward, Matuszek, Cynthia

Over the past decade, the machine learning security community has developed a myriad of defenses for evasion attacks. An understudied question in that community is: for whom do these defenses defend? This work considers common approaches to defending

Externí odkaz: http://arxiv.org/abs/2302.08973

Zobrazit plný text záznamu

Report

Improving Out-of-Distribution Detection via Epistemic Uncertainty Adversarial Training

Autor: Everett, Derek, Nguyen, Andre T., Richards, Luke E., Raff, Edward

The quantification of uncertainty is important for the adoption of machine learning, especially to reject out-of-distribution (OOD) data back to human experts for review. Yet progress has been slow, as a balance must be struck between computational e

Externí odkaz: http://arxiv.org/abs/2209.03148

Zobrazit plný text záznamu

Report

FedSPLIT: One-Shot Federated Recommendation System Based on Non-negative Joint Matrix Factorization and Knowledge Distillation

Autor: Eren, Maksim E., Richards, Luke E., Bhattarai, Manish, Yus, Roberto, Nicholas, Charles, Alexandrov, Boian S.

Non-negative matrix factorization (NMF) with missing-value completion is a well-known effective Collaborative Filtering (CF) method used to provide personalized user recommendations. However, traditional CF relies on the privacy-invasive collection o

Externí odkaz: http://arxiv.org/abs/2205.02359

Zobrazit plný text záznamu

Report

Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech

Autor: Kebe, Gaoussou Youssouf, Richards, Luke E., Raff, Edward, Ferraro, Francis, Matuszek, Cynthia

Learning to understand grounded language, which connects natural language to percepts, is a critical research area. Prior work in grounded language acquisition has focused primarily on textual inputs. In this work we demonstrate the feasibility of pe

Externí odkaz: http://arxiv.org/abs/2112.13758

Zobrazit plný text záznamu

Report

Adversarial Transfer Attacks With Unknown Data and Class Overlap

Autor: Richards, Luke E., Nguyen, André, Capps, Ryan, Forsythe, Steven, Matuszek, Cynthia, Raff, Edward

The ability to transfer adversarial attacks from one model (the surrogate) to another model (the victim) has been an issue of concern within the machine learning (ML) community. The ability to successfully evade unseen models represents an uncomforta

Externí odkaz: http://arxiv.org/abs/2109.11125

Zobrazit plný text záznamu

Report

Practical Cross-modal Manifold Alignment for Grounded Language

Autor: Nguyen, Andre T., Richards, Luke E., Kebe, Gaoussou Youssouf, Raff, Edward, Darvish, Kasra, Ferraro, Frank, Matuszek, Cynthia

We propose a cross-modality manifold alignment procedure that leverages triplet loss to jointly learn consistent, multi-modal embeddings of language-based concepts of real-world items. Our approach learns these embeddings by sampling triples of ancho

Externí odkaz: http://arxiv.org/abs/2009.05147

Zobrazit plný text záznamu