1 code implementation • 21 Jul 2022 • Jennifer J. Sun, Markus Marks, Andrew Ulmer, Dipam Chakraborty, Brian Geuther, Edward Hayes, Heng Jia, Vivek Kumar, Sebastian Oleszko, Zachary Partridge, Milan Peelman, Alice Robie, Catherine E. Schretter, Keith Sheppard, Chao Sun, Param Uttarwar, Julian M. Wagner, Eric Werner, Joseph Parker, Pietro Perona, Yisong Yue, Kristin Branson, Ann Kennedy
We introduce MABe22, a large-scale, multi-agent video and trajectory benchmark to assess the quality of learned behavior representations.
no code implementations • 23 Jul 2020 • Daniel Jiwoong Im, Iljung Kwak, Kristin Branson
A primary difficulty with unsupervised discovery of structure in large data sets is a lack of quantitative evaluation criteria.
no code implementations • NeurIPS Workshop Neuro_AI 2019 • Daniel Jiwoong Im, Rutuja Patil, Kristin Branson
Backpropagation is the workhorse of deep learning, however, several other biologically-motivated learning rules have been introduced, such as random feedback alignment and difference target propagation.
no code implementations • 7 Jun 2019 • Daniel Jiwoong Im, Sridhama Prakhya, Jinyao Yan, Srinivas Turaga, Kristin Branson
The Importance Weighted Auto Encoder (IWAE) objective has been shown to improve the training of generative models over the standard Variational Auto Encoder (VAE) objective.
1 code implementation • 7 Jun 2019 • Iljung S. Kwak, Jian-Zhong Guo, Adam Hantman, David Kriegman, Kristin Branson
In this work, we address the problem of precisely localizing key frames of an action, for example, the precise time that a pitcher releases a baseball, or the precise time that a crowd begins to applaud.
no code implementations • 3 Nov 2018 • Daniel Jiwoong Im, Nakul Verma, Kristin Branson
A common concern with $t$-SNE criterion is that it is optimized using gradient descent, and can become stuck in poor local minima.
no code implementations • ICLR 2018 • Daniel Jiwoong Im, He Ma, Graham Taylor, Kristin Branson
Generative adversarial networks (GANs) have been extremely effective in approximating complex distributions of high-dimensional, input data samples, and substantial progress has been made in understanding and improving GAN performance in terms of both theory and application.
no code implementations • 2 Nov 2017 • Mayank Kabra, Kristin Branson
We give a covering number bound for deep learning networks that is independent of the size of the network.
no code implementations • 13 Dec 2016 • Daniel Jiwoong Im, Michael Tao, Kristin Branson
The success of deep neural networks hinges on our ability to accurately and efficiently optimize high-dimensional, non-convex functions.
no code implementations • 1 Nov 2016 • Eyrun Eyjolfsdottir, Kristin Branson, Yisong Yue, Pietro Perona
We propose a framework for detecting action patterns from motion sequences and modeling the sensory-motor relationship of animals, using a generative recurrent neural network.
no code implementations • CVPR 2015 • Mayank Kabra, Alice Robie, Kristin Branson
As computing the influence of each training example is computationally impractical, we propose a novel distance metric to approximate influence for boosting classifiers that is fast enough to be used interactively.
no code implementations • NeurIPS 2015 • Nakul Verma, Kristin Branson
Metric learning seeks a transformation of the feature space that enhances prediction quality for the given task at hand.