Research Scientist at the National Renewable Energy Lab
Patrick Emami , Aidan Perreault , Jeff Law , David Biagioni , Peter C. St. John . Machine Learning: Science and Technology, 2023. Presented at NeurIPS’22 Workshop on Machine Learning in Structural Biology . [DOI] [arxiv] [Paper code] [EvoProtGrad library] The marginal frequency of each sequence position visualized on the 3D structure of the wild type is the fraction of protein variants in the…
This is the first part of a three part tutorial on using the Intel Neural Compute Stick 2 (NCS2) for vehicle tracking at traffic intersections. The goal of the first part is to get familiar with the NCS2 by walking through how to convert and run a PyTorch MobileNetV2 model on the NCS2 via Windows 10. The following guide should also work for supported popular Linux distros like Ubuntu 18.04.x and…
Patrick Emami , Pan He, Anand Rangarajan, Sanjay Ranka. NeurIPS Object Representations for Learning and Reasoning Workshop. 2020. ( Spotlight presentation ) tl;dr : We identify limitations of applying certain object-centric world models to stochastic environments and propose a state space model and training objective that achieves better stochastic future prediction. Abstract Object-centric world…
Xu, Li, Zhang, Du, Kawarabayashi, Jegelka, 2020 Summary This work proposes a theory they call “algorithmic alignment” to explain why some classes of neural net architectures generalize much better than others on certain reasoning problems. They use PAC learning to derive sample complexity bounds that show that the number of samples needed to achieve a desired amount of generalization increases…
Now that the 2019 London MLSS is over, I thought I’d share a couple things about my experience and summarize some of the fascinating technical content I learned over the 10 days of lectures. This will not only help improve my recall of the material, but will also make it easy to share some of what I learned with my lab and with others that weren’t able to attend. If you find any mistakes, please…
Behbahani et al., 2018 Summary The motivation behind this work is to develop an automated process for learning the behaviors of road users from large amounts of unlabeled video data. A generative model (trained policy) of road user behavior could be used within a larger traffic scene understanding pipeline. In this paper, they propose Horizon GAIL, an imitation-learning algorithm based on GAIL,…
Fujimoto et al., 2018 and Kostrikov et al., 2018 Summary I discuss two recent related papers in the Deep RL literature in this post. The first paper, by Fujimoto et al., introduces techniques for reducing bias and variance in a popular actor-critic method, Deep Deterministic Policy Gradient (DDPG). The second paper, by Kostrikov et al., makes a similar contribution by evaluating and addressing…
Arjona-Medina, Gillhofer, et al., 2018 Intro Delayed rewards is one of the fundamental challenges of reinforcement learning. This paper proposes an algorithm for converting an MDP with delayed rewards into a different MDP with equivalent optimal policies where the delayed reward is now converted into immediate rewards. They accomplish this with “reward redistribution”—a potential solution to the…
Goyal, et al., 2017 Intro A new training procedure for recurrent VAEs is proposed. Recall that for VAEs, we model a joint distribution over observations $x$ and latent variables $z$, and assume that $z$ is involved in the generation of $x$. This distribution is parameterized by $\theta$. Maximizing the marginal log-likelihood $p_{\theta}(x)$ wrt $\theta$ is intractable bc it requires integrating…
Liang, Zhu, Zhu, 2018 Summary This paper looks at tracking severely occluded objects in long video sequences. I like this passage: Although some recent work adopted deep neural networks to extract contexts for object detection and tracking, these data-driven feedforward methods have well-known problems: i) They are black-box models that cannot be explained and only applicable with supervised…