Search Results for author: Amir Sadovnik

Found 7 papers, 0 papers with code

Finding your Lookalike: Measuring Face Similarity Rather than Face Identity

no code implementations13 Jun 2018 Amir Sadovnik, Wassim Gharbi, Thanh Vu, Andrew Gallagher

In this work we propose the new, subjective task of quantifying perceived face similarity between a pair of faces.

Face Recognition General Classification

A Mixed Bag of Emotions: Model, Predict, and Transfer Emotion Distributions

no code implementations CVPR 2015 Kuan-Chuan Peng, Tsuhan Chen, Amir Sadovnik, Andrew C. Gallagher

First, we show through psychovisual studies that different people have different emotional reactions to the same image, which is a strong and novel departure from previous work that only records and predicts a single dominant emotion for each image.

Unaligned Sequence Similarity Search Using Deep Learning

no code implementations16 Sep 2019 James K. Senter, Taylor M. Royalty, Andrew D. Steen, Amir Sadovnik

If our database is labeled this can provide labels for a query gene as is done in traditional methods.

Clustering

A Simulated Experiment to Explore Robotic Dialogue Strategies for People with Dementia

no code implementations18 Apr 2021 Fengpei Yuan, Amir Sadovnik, Ran Zhang, Devin Casenhiser, Eun Jin Paek, Si On Yoon, Xiaopeng Zhao

People with Alzheimer's disease and related dementias (ADRD) often show the problem of repetitive questioning, which brings a great burden on persons with ADRD (PwDs) and their caregivers.

Q-Learning

Redefining "Hallucination" in LLMs: Towards a psychology-informed framework for mitigating misinformation

no code implementations1 Feb 2024 Elijah Berberette, Jack Hutchins, Amir Sadovnik

In recent years, large language models (LLMs) have become incredibly popular, with ChatGPT for example being used by over a billion users.

Hallucination Misinformation

The Path To Autonomous Cyber Defense

no code implementations12 Apr 2024 Sean Oesch, Phillipe Austria, Amul Chaulagain, Brian Weber, Cory Watson, Matthew Dixson, Amir Sadovnik

Defenders are overwhelmed by the number and scale of attacks against their networks. This problem will only be exacerbated as attackers leverage artificial intelligence to automate their workflows.

Cannot find the paper you are looking for? You can Submit a new open access paper.