Adam Lesnikowski


Hello! This is the website of Adam Lesnikowski

Professional Interests

I am very interested in machine learning, active learning, DL and AI. I am espeically interested in computer vision applications.

Current Position

I've been at NVIDIA in Santa Clara, CA since the beginning of 2017. I am a Machine Learning Scientist working on creating optimal data sets and learning with limited labels. Towards this we are using techniques from the active learning, uncertainty and Bayesian deep learning communities, among others. I've very excited to be working on these problems with a great and passionate group of people!

LinkedIn

My LinkedIn profile

Recent Work

Chitta, Kashyap, Jose M. Alvarez, and Adam Lesnikowski. "Deep Probabilistic Ensembles: Approximate Variational Inference through KL Regularization." arXiv preprint arXiv:1811.02640 (2018). NuerIPS Workshop 2018. Link

Zheng, Jiaming, Adam Lesnikowski, and Jose M. Alvarez. "The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning." NeurIPS Workshop 2018.

Chitta, Kashyap, Jose M. Alvarez, and Adam Lesnikowski. "Large-Scale Visual Active Learning with Deep Probabilistic Ensembles." arXiv preprint arXiv:1811.03575 (2018). Link

Select Projects and Talks

Deep Active Learning, talk at the GPU Technology Conference, March 2018.

Predicting Prices for House Shares using Deep Convolutional Neural Networks, project with Rong Yuan, Genevieve Patterson, 2016.

How Much Did it Rain?: Predicting Real Rainfall Totals Based on Polarimetric Radar Data, project with Peter Bartlett and Alexei Efros, 2015.

NP-Completeness Papers by Cook, Levin and Karp, P =?NP, and a Lost Letter, project with Justine Sherry, UC Berkeley CS 294, 2014.

A Geometric Interpretation of the Metaphysics of the Tractatus, project with Professor Paolo Mancosu, 2014.

Reasoning About an Ordering of Theories, my thesis on a modal logic that captures all correct reasoning about mathematical interpretations over the base theory of Peano Arithmetic. pdf

Education

I did my graduate work at UC Berkeley, where I was worked on mathmatical logic, large cardinals and rationality. Before that, I was at the University of Amsterdam's ILLC working on mathmatical logic, theoretical CS and AI. For my undergrad studies, I went to Harvard University, where I studied mathematics and philosophy.

Contact Info

Email: my first name dot last at gmail OR my first initial last name at nvidia.

You can also follow me on Twitter @lesnikow!