research

I’m interested in self-supervised learning, representation learning, curiosity-based exploration, and leveraging internet-scale models and data. I am keen to draw inspiration from intelligence in humans and nature—especially as a goal-post rather than a blueprint. My long-term goal is to develop intelligent agents that can generalize and continually adapt as robustly and efficiently as humans do, allowing them to be safely deployed in the real world.

Publications

2023

1. ⏳ CVPR-23 ⌛

   Internet Explorer: Representation Learning on the Open Web

   Alexander Li*, Ellis Brown*, Alexei A. Efros, and Deepak Pathak

   In Conference on Computer Vision and Pattern Recognition, 2023

   Under Review

2022

1. 

   Internet Curiosity: Directed Unsupervised Learning on Uncurated Internet Data

   Alexander Li*, Ellis Brown*, Alexei A. Efros, and Deepak Pathak

   In European Conference on Computer Vision Workshop on “Self Supervised Learning: What is Next?”, 2022

   Abs Bib Poster

   We show that a curiosity-driven computer vision algorithm can learn to efficiently query Internet text-to-image search engines for images that improve the model’s performance on a specified dataset. In contrast to typical self-supervised computer vision algorithms, which learn from static datasets, our model actively expands its training set with the most relevant images. First, we calculate the image-level curiosity reward as the negative distance of an image’s representation to its nearest neighbor in the targeted dataset. This reward is easily estimated using only unlabeled data from the targeted dataset, and can be aggregated into a query-level reward that effectively identifies useful queries. Second, we use text embedding similarity scores to propagate observed curiosity rewards to untried text queries. This efficiently identifies relevant semantic clusters without any need for class labels or label names from the targeted dataset. Our method significantly outperforms models that require 1-2 orders of magnitude more compute and data.

   @inproceedings{li2022internetcuriosity,
     title = {Internet Curiosity: Directed Unsupervised Learning on Uncurated Internet Data},
     author = {Li*, Alexander and Brown*, Ellis and Efros, Alexei A. and Pathak, Deepak},
     year = {2022},
     booktitle = {European Conference on Computer Vision Workshop on ``Self Supervised Learning: What is Next?''},
     address = {Tel Aviv, Israel},
   }

2018

1. 

   An Architecture for Spatiotemporal Template-Based Search

   Ellis Brown, Soobeen Park, Noel Wardord, Adriane Seiffert, and 3 more authors

   Advances in Cognitive Systems, 2018

   Abs Bib PDF

   Visual search for a spatiotemporal target occurs frequently in human experience—from military or aviation staff monitoring complex displays of multiple moving objects to daycare teachers monitoring a group of children on a playground for risky behaviors. In spatiotemporal search, unlike more traditional visual search tasks, the target cannot be identified from a single frame of visual experience; as the target is a spatiotemporal pattern that unfolds over time, detection of the target must also integrate information over time. We propose a new computational cognitive architecture used to model and understand human visual attention in the specific context of visual search for a spatiotemporal target. Results from a previous human participant study found that humans show interesting attentional capacity limitations in this type of search task. Our architecture, called the SpatioTemporal Template-based Search (STTS) architecture, solves the same search task from the study using a wide variety of parameterized models that each represent a different cognitive theory of visual attention from the psychological literature. We present results from initial computational experiments using STTS as a first step towards understanding the computational nature of attentional bottlenecks in this type of search task, and we discuss how continued STTS experiments will help determine which theoretical models best explain the capacity limitations shown by humans. We expect that results from this research will help refine the design of visual information displays to help human operators perform difficult, real-world monitoring tasks.

   @article{brown2018stts,
     title = {An Architecture for Spatiotemporal Template-Based Search},
     author = {Brown, Ellis and Park, Soobeen and Wardord, Noel and Seiffert, Adriane and Kawamura, Kazuhiko and Lappin, Joseph and Kunda, Maithilee},
     year = {2018},
     journal = {Advances in Cognitive Systems},
     volume = {6},
     pages = {101--118},
   }

2. ACS-18

   SpatioTemporal Template-based Search: An Architecture for Spatiotemporal Template-Based Search

   Ellis Brown, Soobeen Park, Noel Warford, Adriane Seiffert, and 3 more authors

   In Proceedings of the 6th Conference on Advances in Cognitive Systems, Aug 2018

   PDF Slides

Talks

2021

1. 

   Linearly Constrained Separable Optimization

   Ellis Brown, Nicholas Moehle, and Mykel J. Kochenderfer

   In JuliaCon 2021 JuMP Track, Jul 2021

   Abs Blog Video

   Many optimization problems involve minimizing a sum of univariate functions, each with a different variable, subject to coupling constraints. We present PiecewiseQuadratics.jl and SeparableOptimization.jl, two Julia packages for solving such problems when these univariate functions in the objective are piecewise-quadratic.

2019

1. AISES-19

   Modeling Uncertainty in Bayesian Neural Networks with Dropout: The effect of weight prior and network architecture selection

   Ellis Brown*, Melanie Manko*, and Ethan Matlin*

   In American Indian Science and Engineering Society National Conference, Oct 2019

   🎖️ Third Place, Graduate Student Research Competition

   Abs Poster

   While neural networks are quite successful at making predictions, these predictions are usually point estimates lacking any notion of uncertainty. However, when fed data very different from its training data, it is useful for a neural network to realize that its predictions could very well be wrong and encode that information through uncertainty bands around its point estimate prediction. Bayesian Neural Networks trained with Dropout are a natural way of modeling this uncertainty with theoretical foundations relating them to Variational Inference approximating Gaussian Process posteriors. In this paper, we investigate the effects of weight prior selection and network architecture on uncertainty estimates derived from Dropout Bayesian Neural Networks.

2017

1. AISES-17

   Computational Cognitive Systems to Model Information Salience

   Ellis Brown, Adriane Seiffert, Noel Warford, Soobeen Park, and 1 more author

   In American Indian Science and Engineering Society National Conference, Sep 2017

   Abs Slides Website

   This project seeks to model human information salience—in this case, how much a person will notice a piece of visual information—using an approach from artificial intelligence that involves building computational cognitive systems models of human performance on certain tasks. Too much visual information can be overwhelming, making it difficult for people to discern the important parts. This can be detrimental in many situations where visual attention is crucial, such as air traffic control systems, military information displays, or TSA screening stations. Results from a previous human participant study found that humans show interesting limitations in attentional capacity when asked to monitor a complex moving display. We create artificial computational agents based on various cognitive models of visual attention to solve the same visual information salience task and run computational experiments to measure cognitive performance. In follow-up work, we will compare the performance of our models to the human data to determine which models best explain the capacity limitations shown by people.

Reports

2022

1. CMU 16-824

   Self-Supervised Representation Learning via Curiosity-Driven Exploration

   Alvin Shek, Ellis Brown, Nilay Pande, and David Noursi

   May 2022

   Abs Website

   “The performance of machine learning methods is heavily dependent on the choice of data representation” — Bengio et al, 2012.
   As machine learning continues to be applied to more complex and important tasks, this dependence on the data representation will only increase. While current machine learning methods are bottlenecked by representation quality, current methods for learning representations are bottlenecked on the dataset size. But this process of creating large static datasets, as is the mainstream practice, is expensive, time consuming, and heavily prone to human bias.
   Machine learning practitioners have increasingly been focusing on paradigms such as unsupervised and self-supervised learning to help alleviate the expense of supervision in working with bigger datasets; however, these methods still suffer from the issues of static datasets. One promising approach to learn good representations without a fixed datasets is by directly interacting with the environment. The visual state space of real environments/simulators can be quite huge and intractable to explore fully. Hence, in this project, we investigate intelligent curiosity driven exploration strategies to learn good representations from a simulator using self supervised learning objectives. We discuss the effectiveness of different strategies, issues and future directions of research in this field.

2021

1. CMU 16-811

   Scaling Interpretable Reinforcement Learning via Decision Trees to Minecraft

   Ellis Brown, and Aaron M. Roth

   Dec 2021

   Abs PDF

   Deep reinforcement learning is a powerful tool for learning complex control tasks; however, neural networks are notoriously “black boxes” and lack many properties desirable of autonymous systems deployed in safety critical environments. In this project, we focus on methods that result in a final control policy specified via a decision tree—which is thus interpretable and verifiable. We build upon a prior method, VIPER, that first learns a high-performing “expert” policy via any standard Deep RL technique, and then distills the expert policy into a decision tree. Our method, called MSVIPER, is specifically designed to scale to complex environements that greatly benefit from (or require) curriculum learning to be solved; we leverage the structure in the currculum stages to enable more efficient learning and a smaller (and thus more interpretable) decision tree. To demonstrate the ability of our method to succeed in complex environments, we apply it to Minecraft—a challenging open-world environment. We highlight that our method is amennable to post-training verification and modification or improvement.

2020

1. Stanford CS 361

   Securities Lending Policy Optimization

   Ellis Brown

   Jun 2020

   Abs PDF

   This paper presents a method to determine an optimal policy for the lending of securities by large institutions in the securities finance market as a final project for the Stanford University AA222 Engineering Design Optimization class. The securities lending process is formulated as a Markov decision process in which the lender decides whether to accept or reject incoming offers from borrowers. This formulation allows for a policy that maximizes the expected return with each decision to be derived using dynamic programming. The framework presented is easily extensible through the creation of more realistic models of the dynamics of the securities lending market.

2019

1. Columbia CS E6699

   Modeling Uncertainty in Bayesian Neural Networks with Dropout

   Ellis Brown*, Melanie Manko*, and Ethan Matlin*

   May 2019

   Abs PDF Slides

   While neural networks are quite successful at making predictions, these predictions are usually point estimates lacking any notion of uncertainty. However, when fed data very different from its training data, it is useful for a neural network to realize that its predictions could very well be wrong and encode that information through uncertainty bands around its point estimate prediction. Bayesian Neural Networks trained with Dropout are a natural way of modeling this uncertainty with theoretical foundations relating them to Variational Inference approximating Gaussian Process posteriors. In this paper, we investigate the effects of weight prior selection and network architecture on uncertainty estimates derived from Dropout Bayesian Neural Networks.