Search Results for author:
Found 12 papers, 2 papers with code
Designing a Communication Bridge between Communities: Participatory Design for a Question-Answering AI Agent
How do we design an AI system that is intended to act as a communication bridge between two user communities with different mental models and vocabularies?
Human-AI Interaction Design in Machine Teaching
Machine Teaching (MT) is an interactive process where a human and a machine interact with the goal of training a machine learning model (ML) for a specified task.
ReFace: Real-time Adversarial Attacks on Face Recognition Systems
We find that the white-box attack success rate of a pure U-Net ATN falls substantially short of gradient-based attacks like PGD on large face recognition datasets.
Explanation as Question Answering based on a Task Model of the Agent's Design
We describe a stance towards the generation of explanations in AI agents that is both human-centered and design-based.
A Framework for Interactive Knowledge-Aided Machine Teaching
Machine Teaching (MT) is an interactive process where humans train a machine learning model by playing the role of a teacher.
Agent Smith: Teaching Question Answering to Jill Watson
We describe Agent Smith, an interactive machine teaching agent that reduces the time taken to train a Jill for a new online class by an order of magnitude.
WeightScale: Interpreting Weight Change in Neural Networks
Interpreting the learning dynamics of neural networks can provide useful insights into how networks learn and the development of better training and design approaches.
Investigating Learning in Deep Neural Networks using Layer-Wise Weight Change
Understanding the per-layer learning dynamics of deep neural networks is of significant interest as it may provide insights into how neural networks learn and the potential for better training regimens.
A Genetic Algorithm Based Approach for Satellite Autonomy
The genetic algorithm was successfully able to produce this result for all the starting orbits.
Benchmarking Differentially Private Residual Networks for Medical Imagery
In this paper we measure the effectiveness of $\epsilon$-Differential Privacy (DP) when applied to medical imaging.
A Deeper Look at the Unsupervised Learning of Disentangled Representations in $β$-VAE from the Perspective of Core Object Recognition
(DiCarlo et al., 2012) Various computational perceptual models have been built to attempt and tackle the object identification task in an artificial perceptual setting.
A Closer Look at Disentangling in $β$-VAE
In many data analysis tasks, it is beneficial to learn representations where each dimension is statistically independent and thus disentangled from the others.
