Braden Hancock
ML Researcher, Developer, and Entrepreneur
I'm having the time of my life as Co-founder and Head of Technology at Snorkel AI! We're making AI practical with a new data-first approach to ML.
Research interests:
machine learning systems, weak supervision, multi-task learning (MTL), transfer learning, training data creation, learning from natural language, information extraction, natural language processing (NLP)


  • Jul. 2020: Snorkel AI came out of stealth, featured by Forbes, Greylock, GV, and others!
  • Apr. 2020: I gave a 60-min interview about Snorkel on the Software Engineering Daily podcast.
  • Sep. 2019: I gave an invited talk on Snorkel at the Data Science fwdays'19 conference in Kiev, Ukraine.
  • Aug. 2019: Snorkel v0.9 is live! Check out the new website, repo, blog, and tutorials!
  • Aug. 2019: The self-feeding chatbot was featured on the Facebook blog.

  • Jul. 2019: Our paper on using Snorkel to build a KB of gene-phenotype relations from literature was published in Nature Comms.
  • Jul. 2019: I presented on the self-feeding chatbot at ACL 2019.

  • Jun. 2019: The Snorkel Workshop was a huge success, with 55 collaborators from industry/gov't/medicine.

  • Jun. 2019: We achieved a new state-of-the-art score on the SuperGLUE Benchmark and a majority of its tasks with Snorkel!

  • May 2019: I presented Title Generation for Web Tables at WWW 2019.

  • Apr. 2019: I defended my dissertation on "Weak Supervision from High-Level Abstractions"—thank you to so many!

  • Mar. 2019: The Snorkel MeTaL team I lead achieved a new state of the art on the GLUE Benchmark! Check out blog post.

  • Mar. 2019: Google published a blog post on our collaboration applying Snorkel at industrial scale to pool organizational knowledge.
  • Mar. 2019: We published a blog post on weak supervision on the Stanford AI Lab blog.

  • Mar. 2019: Snorkel Drybell, a collaboration between the Snorkel project and Google, was accepted to SIGMOD 2019.


Snorkel AI
Co-founders: Alex Ratner, Chris Ré, Paroma Varma, Henry Ehrenberg
Topics: AI application development and deployment
Stanford University
Groups: Stanford Hazy Research, Stanford DAWN, Stanford NLP Group, Stanford StatsML
Advisor: Chris Ré, Dissertation: slides
Topics: Weak supervision, multi-task learning, information extraction
Fall 2018
Groups: Facebook AI Research (FAIR) - Paris
Mentors: Jason Weston, Antoine Bordes
Topics: Self-feeding chatbots, learning from dialogue, multi-task learning
Summer 2017
Groups: Google Brain, Google Search - Mountain View
Mentors: Hongrae Lee, Cong Yu, Quoc Le
Topics: Abstractive summarization of semi-structured content, recurrent neural networks
MIT Lincoln Laboratory
Summers 2014-2015
Group: Computing & Analytics - Boston
Mentors: Vijay Gadepally, Jeremy Kepner
Topics: Recommender systems for Department of Defense applications, cryptography
Johns Hopkins University
Summer 2013
Group: Human Language Technology Center of Excellence - Baltimore
Mentors: Mark Dredze, Glen Coppersmith
Topics: Public health trend extraction from social media, topic modeling

Brigham Young University
Group: Design Exploration Research Group
Mentor: Chris Mattson
Topics: Multi-objective optimization, design space exploration
Air Force Research Laboratory
Summer 2011
Group: Turbine Engine Division
Mentor: John Clark
Topics: Evolutionary algorithms for optimization, turbine engine simulation


Snorkel Flow: The Data-First Platform for Enterprise AI
AI solutions are often blocked on one crucial ingredient — the massive labeled training datasets that fuel modern approaches. Snorkel Flow is a first-of-its-kind platform that focuses on a revolutionary programmatic approach to labeling, building, and managing these training datasets, enabling a new level of rapid, iterative development and deployment of AI applications:
Snorkel: A System for Fast Training Data Creation
Snorkel is a system for rapidly creating, modeling, and managing training data. It is the flagship implementation of the new data programming paradigm for supporting weak supervision resources. Development is ongoing, with collaborators and active users at over a dozen major technical and medical organizations (e.g., Google, Microsoft, Intel, Toshiba, JPL, Alibaba, Stanford Medicine, etc.) and 1000+ stars on Github. I am one of the core developers and maintainers of the Snorkel project, including a recent reimplementation from scratch for improved speed, ease of use, and MTL support as a part of Snorkel MeTaL.
VLDB 2018 (oral), Ongoing
"Best of VLDB"
Snorkel MeTaL: Weak Supervision for Multi-Task Learning
We extend Snorkel to multi-tasking supervision and multi-task learning (MTL). In particular, we are interested in the massive multi-task learning regime where we have large numbers of tasks and labels of varying types, granularities, and label accuracies. Using Snorkel MeTaL, we achieved new state-of-the-art scores on the GLUE Benchmark and four of its component tasks.
AAAI 2019 (oral), DEEM (SIGMOD) 2018 (oral), Ongoing
Software 2.0: Learning-Centric Software Stacks
Driven by accuracy improvements and deployment advantages, many organizations have begun to shift toward learning-centered software stacks. That is, "Software 1.0" code with explicit instructions written by programmers is being replaced by "Software 2.0" code that is written in the weights of neural networks. In this paradigm, training data becomes the primary interface through which developers interact with their Software 2.0 systems. This requires a new level of scalability, control, and efficiency when it comes to generating and shaping training sets. We are exploring the ramifications of this new programming model and building the tools to support it.
CIDR 2019 (oral), Ongoing
Self-Feeding Chatbots
Most of the conversations a chatbot sees over its lifetime happen after it's deployed. These conversations aren't typically useable as training data, but give the chatbot the right tools and it can learn from those too! We introduced a multi-task "self-feeding" chatbot that knows how to extract new training examples from the conversations it participates in to improve itself further after it's deployed.
Babble Labble: Learning from Natural Language Explanations
We explore collecting natural language explanations for why annotators give the labels they do and parsing these into executable functions, which can then be used to generate noisy labels for large amounts of unlabeled data. The resulting probabalistically labeled training dataset can then be used to train a powerful downstream discriminative model for the task at hand. We find that utilizing these natural language explanations allows real-world users to train classifiers with comparable F1 scores up to 100 times faster than when they provide just labels.
ACL 2018 (oral), NeurIPS 2017 Demo
Fonduer: Knowledge Base Construction from Richly Formatted Data
We introduce an information extraction framework that utilizes multiple representations of the data (structural, tabular, visual, and textual) to achieve state-of-the-art performance in four real-world extraction taks. Our framework is currently in use commercially at Alibaba and with law enforcement agencies fighting online human trafficking.
SIGMOD 2018 (oral)
A Machine-Compiled Database of Genome-Wide Association Studies (Nature Comms)
Using the multi-modal parsing and extraction tools from Fonduer and learning and inference tools from Snorkel, we construct a knowledge base of genotype/phenotype associations extracted from the text and tables in ~600 open-access papers from PubMed Central. Our system expands existing manually curated databases by approximately 20% with 92% precision.
Bio-Ontologies 2017, NeurIPS 2017 MLCB Workshop
Generating Titles for Web Tables
We introduce a framework for generating titles for tables that are displayed out of their original context. We use a pointer-generator network, a sequence-to-sequence model that is capable of both generating tokens and copying tokens from the input (such as rare and out-of-vocab words), resulting in titles that are both relevant and readable.
The Web Conference (WWW) 2019
Collective Supervision of Topic Models for Predicting Surveys with Social Media
We use topic models to correlate social media messages with survey outcomes and to provide an interpretable representation of the data. Rather than rely on fully unsupervised topic models, we use existing aggregated survey data to inform the inferred topics, a class of topic model supervision referred to as collective supervision.
AAAI 2016
Recommender Systems for the Department of Defense and Intelligence Community
With an internal committee of 20 MIT and DoD researchers, I spearheaded the construction of this report, which formalizes the components and complexities of recommender systems and surveys their existing and potential uses in the Department of Defense and U.S. Intelligence community.
MITLL Journal 2016

QALF: Information Extraction for the Long Tail via Question Answering
We use a Question Answering (QA) model as a flexible means of converting domain expertise expressed as natural language into weak supervision resources (labeling functions, or LFs). Preliminary results suggest that with as few as a dozen user inputs (domain-relevant questions), we can quickly build first-order extractors for new relations that lack distant supervision resources.
L-dominance: An approximate-domination mechanism for adaptive resolution of Pareto frontiers
We propose a mechanism called L-dominance (based on the Lamé curve) which promotes adaptive resolution of solutions on the Pareto frontier for evolutionary multi-objective optimization algorithms.
SMO Journal, AIAA ASM 2015, Honors Thesis
Best Student Paper
Reducing Shock Interactions in a High Pressure Turbine via 3D Aerodynamic Shaping
We show that the shock wave reflections inside a turbine engine can be approximated by calculating the 3D surface normal projections of the airfoils. Using a genetic algorithm, We produce superior airfoil geometries (with respect to high cycle fatigue failure) four orders of magnitude faster than the traditional CFD-based approach.
AIAA Journal, AIAA ASM 2014
Best Student Paper
The Smart Normal Constraint Method for Directly Generating a Smart Pareto Set
We introduce the Smart Normal Constraint (SNC) method, the first method capable of directly generating a smart Pareto set (a Pareto set in which the density of solutions varies such that regions of significant tradeoff have the greatest resolution). This is accomplished by iteratively updating an approximation of the design space geometry, which is used to guide subsequent searches in the design space.
SMO Journal, AIAA MDO 2013
Usage Scenarios for Design Space Exploration with a Dynamic Multiobjective Optimization Formulation
We investigate three usage scenarios for formulation space exploration, building on previous work that introduced a new way to formulate multi-objective problems, allowing a designer to change up update design objectives, constraints, and variables in a fluid manner that promotes exploration.
RiED Journal, ASME DETC 2012
Best Paper


Stanford University
Ph.D. Computer Science (Jun. 2019)
Advisor: Chris Ré
Machine Learning Emphasis (GPA 4.00)
Brigham Young University
B.S. Mechanical Engineering, Mathematics Minor (Apr. 2015)
Advisor: Chris Mattson
Valedictorian, summa cum laude (GPA 4.00)


National Science Foundation Graduate Research Fellowship (NSF GRF)
National Defense Science and Engineering Graduate Fellowship (NDSEG)
2015 (declined for incompatibility with NSF)
Phi Kappa Phi Marcus L. Urann Fellowship
2015 (1 of 6 in USA)
Stanford School of Engineering Finch Family Fellowship
AIAA Vicki and George Muellner Scholarship
2014 (1 of 1 in USA)

Barry M. Goldwater Scholarship
AIAA Orville and Wilbur Wright Scholarship
2013 (1 of 3 in USA)
ASME Kenneth Andrew Roe Scholarship
2012 (1 of 1 in USA)
National Merit Scholarship
BYU Thomas S. Monson Presidential Scholarship
2011 (1 of 50)