Výsledky vyhledávání - "A. FONSECA, João"

Report

Output Scouting: Auditing Large Language Models for Catastrophic Responses

Autor: Bell, Andrew, Fonseca, Joao

Recent high profile incidents in which the use of Large Language Models (LLMs) resulted in significant harm to individuals have brought about a growing interest in AI safety. One reason LLM safety issues occur is that models often have at least some

Externí odkaz: http://arxiv.org/abs/2410.05305

Zobrazit plný text záznamu

Report

Development of Machine Learning Classifiers for Blood-based Diagnosis and Prognosis of Suspected Acute Infections and Sepsis

Autor: Buturovic, Ljubomir, Mayhew, Michael, Luethy, Roland, Choi, Kirindi, Midic, Uros, Damaraju, Nandita, Hasin-Brumshtein, Yehudit, Pratap, Amitesh, Adams, Rhys M., Fonseca, Joao, Srinath, Ambika, Fleming, Paul, Pereira, Claudia, Liesenfeld, Oliver, Khatri, Purvesh, Sweeney, Timothy

We applied machine learning to the unmet medical need of rapid and accurate diagnosis and prognosis of acute infections and sepsis in emergency departments. Our solution consists of a Myrna (TM) Instrument and embedded TriVerity (TM) classifiers. The

Externí odkaz: http://arxiv.org/abs/2407.02737

Zobrazit plný text záznamu

Report

Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunity

Autor: Bell, Andrew, Fonseca, Joao, Abrate, Carlo, Bonchi, Francesco, Stoyanovich, Julia

Algorithmic recourse -- providing recommendations to those affected negatively by the outcome of an algorithmic system on how they can take action and change that outcome -- has gained attention as a means of giving persons agency in their interactio

Externí odkaz: http://arxiv.org/abs/2401.16088

Zobrazit plný text záznamu

Report

ShaRP: Explaining Rankings with Shapley Values

Autor: Pliatsika, Venetia, Fonseca, Joao, Wang, Tilun, Stoyanovich, Julia

Algorithmic decisions in critical domains such as hiring, college admissions, and lending are often based on rankings. Because of the impact these decisions have on individuals, organizations, and population groups, there is a need to understand them

Externí odkaz: http://arxiv.org/abs/2401.16744

Zobrazit plný text záznamu

Report

Setting the Right Expectations: Algorithmic Recourse Over Time

Autor: Fonseca, Joao, Bell, Andrew, Abrate, Carlo, Bonchi, Francesco, Stoyanovich, Julia

Algorithmic systems are often called upon to assist in high-stakes decision making. In light of this, algorithmic recourse, the principle wherein individuals should be able to take action against an undesirable outcome made by an algorithmic system,

Externí odkaz: http://arxiv.org/abs/2309.06969

Zobrazit plný text záznamu

Report

Research Trends and Applications of Data Augmentation Algorithms

Autor: Fonseca, Joao, Bacao, Fernando

In the Machine Learning research community, there is a consensus regarding the relationship between model complexity and the required amount of data and computation power. In real world applications, these computational requirements are not always av

Externí odkaz: http://arxiv.org/abs/2207.08817

Zobrazit plný text záznamu