no code implementations • 1 Aug 2023 • Jeonghyun Lee, Vrinda Nandan, Harshvardhan Sikka, Spencer Rugaber, Ashok Gole
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?
no code implementations • 10 Jun 2022 • Karan Taneja, Harshvardhan Sikka, Ashok Goel
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.
no code implementations • 9 Jun 2022 • Shehzeen Hussain, Todd Huster, Chris Mesterharm, Paarth Neekhara, Kevin An, Malhar Jere, Harshvardhan Sikka, Farinaz Koushanfar
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.
no code implementations • 8 Jun 2022 • Ashok Goel, Harshvardhan Sikka, Vrinda Nandan, Jeonghyun Lee, Matt Lisle, Spencer Rugaber
We describe a stance towards the generation of explanations in AI agents that is both human-centered and design-based.
no code implementations • 21 Apr 2022 • Karan Taneja, Harshvardhan Sikka, Ashok Goel
Machine Teaching (MT) is an interactive process where humans train a machine learning model by playing the role of a teacher.
no code implementations • 22 Dec 2021 • Ashok Goel, Harshvardhan Sikka, Eric Gregori
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.
no code implementations • 7 Jul 2021 • Ayush Manish Agrawal, Atharva Tendle, Harshvardhan Sikka, Sahib Singh
Interpreting the learning dynamics of neural networks can provide useful insights into how networks learn and the development of better training and design approaches.
2 code implementations • 13 Nov 2020 • Ayush Manish Agrawal, Atharva Tendle, Harshvardhan Sikka, Sahib Singh, Amr Kayid
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.
no code implementations • 27 Oct 2020 • Sidhdharth Sikka, Harshvardhan Sikka
The genetic algorithm was successfully able to produce this result for all the starting orbits.
1 code implementation • 27 May 2020 • Sahib Singh, Harshvardhan Sikka, Sasikanth Kotti, Andrew Trask
In this paper we measure the effectiveness of $\epsilon$-Differential Privacy (DP) when applied to medical imaging.
no code implementations • 25 Apr 2020 • Harshvardhan Sikka
(DiCarlo et al., 2012) Various computational perceptual models have been built to attempt and tackle the object identification task in an artificial perceptual setting.
no code implementations • 11 Dec 2019 • Harshvardhan Sikka, Weishun Zhong, Jun Yin, Cengiz Pehlevan
In many data analysis tasks, it is beneficial to learn representations where each dimension is statistically independent and thus disentangled from the others.