J
Jason Yosinski
Researcher at Uber
Publications - 72
Citations - 21503
Jason Yosinski is an academic researcher from Uber . The author has contributed to research in topics: Artificial neural network & Convolutional neural network. The author has an hindex of 37, co-authored 70 publications receiving 17256 citations. Previous affiliations of Jason Yosinski include Cornell University & Columbia University.
Papers
More filters
Patent
Methods and systems for pattern characteristic detection
Dechant Alan Chad,Hod Lipson,Rebecca J. Nelson,Michael A. Gore,Tyr Wiesner-Hanks,Ethan L. Stewart,Jason Yosinski,Siyuan Chen +7 more
TL;DR: In this paper, a method to detect pattern characteristics in target specimens that includes acquiring sensor data for the target specimens, dividing the acquired sensor data into a plurality of data segments, and generating, by multiple neural networks, multiple respective output matrices, with each data element of the multiple respective outputs being representative of a probability that corresponding sensor data of a respective one of the data segments includes a pattern characteristic in the target objects.
Journal ArticleDOI
RxRx1: A Dataset for Evaluating Experimental Batch Correction Methods
Maciej Sypetkowski,Morteza Rezanejad,Saber Saberian,Oren Kraus,John Urbanik,James Nick Taylor,Ben Mabey,Mason Lemoyne Victors,Jason Yosinski,Alborz Rezazadeh Sereshkeh,Imran S. Haque,Berton A. Earnshaw +11 more
TL;DR: RxRx1 as mentioned in this paper is a dataset of 125,510 high-resolution microscopy images of human cells under 1,138 genetic perturbations in 51 experimental batches across 4 cell types.
Posted Content
GSNs : Generative Stochastic Networks
Guillaume Alain,Yoshua Bengio,Li Yao,Jason Yosinski,Éric Thibodeau-Laufer,Saizheng Zhang,Pascal Vincent +6 more
TL;DR: Generative stochastic networks (GSN) as discussed by the authors learn the transition operator of a Markov chain whose stationary distribution estimates the data distribution, which is an alternative to maximum likelihood.
Posted Content
MAV Stabilization using Machine Learning and Onboard Sensors
Jason Yosinski,Cooper Bills +1 more
TL;DR: This research explores using machine learning to predict the drift (flight path errors) of an MAV while executing a desired flight path, which will allow the MAV to adjust it's flightpath to maintain a desired course.