Jason Yosinski

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

TMLR

Plug and Play Language Models: A Simple Approach to Controlled Text Generation

ICLR 2020 1

Measuring the Intrinsic Dimension of Objective Landscapes

measuring-the-intrinsic-dimension-of-1

SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability

svcca-singular-vector-canonical-correlation-1

Convergent Learning: Do different neural networks learn the same representations?

arXiv 2015

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images

deep-neural-networks-are-easily-fooled-high-1

Rosanne Liu

Andrea Madotto

Jascha Sohl-Dickstein

Jeff Clune

Aarohi Srivastava

researcher

Abhinav Rastogi

researcher

Abhishek Rao

Abu Awal Md Shoeb

Abubakar Abid

Adam Fisch