Timezone: »
Deep neural networks (DNNs) have demonstrated state-of-the-art results on many pattern recognition tasks, especially vision classification problems. Understanding the inner workings of such computational brains is both fascinating basic science that is interesting in its own right---similar to why we study the human brain---and will enable researchers to further improve DNNs. One path to understanding how a neural network functions internally is to study what each of its neurons has learned to detect. One such method is called activation maximization, which synthesizes an input (e.g. an image) that highly activates a neuron. Here we dramatically improve the qualitative state of the art of activation maximization by harnessing a powerful, learned prior: a deep generator network. The algorithm (1) generates qualitatively state-of-the-art synthetic images that look almost real, (2) reveals the features learned by each neuron in an interpretable way, (3) generalizes well to new datasets and somewhat well to different network architectures without requiring the prior to be relearned, and (4) can be considered as a high-quality generative method (in this case, by generating novel, creative, interesting, recognizable images).
Author Information
Anh Nguyen (University of Wyoming)
Alexey Dosovitskiy (University of Freiburg)
Jason Yosinski (Cornell)
Dr. Jason Yosinski is a machine learning researcher, was a founding member of Uber AI Labs, and is scientific adviser to Recursion Pharmaceuticals and several other companies. His work focuses on building more capable and more understandable AI. As scientists and engineers build increasingly powerful AI systems, the abilities of these systems increase faster than does our understanding of them, motivating much of his work on AI Neuroscience: an emerging field of study that investigates fundamental properties and behaviors of AI systems. Dr. Yosinski completed his PhD as a NASA Space Technology Research Fellow working at the Cornell Creative Machines Lab, the University of Montreal, Caltech/NASA Jet Propulsion Laboratory, and Google DeepMind. His work on AI has been featured on NPR, Fast Company, the Economist, TEDx, XKCD, and on the BBC. Prior to his academic career, Jason cofounded two web technology companies and started a program in the Los Angeles school district that teaches students algebra via hands-on robotics. In his free time, Jason enjoys cooking, sailing, motorcycling, reading, paragliding, and sometimes pretending he's an artist.
Thomas Brox (University of Freiburg)
Jeff Clune (University of Wyoming)
More from the Same Authors
-
2021 : Nearest-neighbor is more useful than feature attribution in improving human accuracy on image classification »
Giang Nguyen · Anh Nguyen -
2022 : Towards Discovering Neural Architectures from Scratch »
Simon Schrodi · Danny Stoll · Robin Ru · Rhea Sukthanker · Thomas Brox · Frank Hutter -
2022 Poster: Assaying Out-Of-Distribution Generalization in Transfer Learning »
Florian Wenzel · Andrea Dittadi · Peter Gehler · Carl-Johann Simon-Gabriel · Max Horn · Dominik Zietlow · David Kernert · Chris Russell · Thomas Brox · Bernt Schiele · Bernhard Schölkopf · Francesco Locatello -
2022 Poster: Visual correspondence-based explanations improve AI robustness and human-AI team accuracy »
Mohammad Reza Taesiri · Giang Nguyen · Anh Nguyen -
2021 Poster: The effectiveness of feature attribution methods and its correlation with automatic evaluation scores »
Giang Nguyen · Daeyoung Kim · Anh Nguyen -
2020 Poster: Supermasks in Superposition »
Mitchell Wortsman · Vivek Ramanujan · Rosanne Liu · Aniruddha Kembhavi · Mohammad Rastegari · Jason Yosinski · Ali Farhadi -
2020 Poster: COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning »
Simon Ging · Mohammadreza Zolfaghari · Hamed Pirsiavash · Thomas Brox -
2019 : Panel - The Role of Communication at Large: Aparna Lakshmiratan, Jason Yosinski, Been Kim, Surya Ganguli, Finale Doshi-Velez »
Aparna Lakshmiratan · Finale Doshi-Velez · Surya Ganguli · Zachary Lipton · Michela Paganini · Anima Anandkumar · Jason Yosinski -
2019 : How Meta-Learning Could Help Us Accomplish Our Grandest AI Ambitions, and Early, Exotic Steps in that Direction »
Jeff Clune -
2019 Poster: Hamiltonian Neural Networks »
Sam Greydanus · Misko Dzamba · Jason Yosinski -
2019 Poster: DeepUSPS: Deep Robust Unsupervised Saliency Prediction via Self-supervision »
Tam Nguyen · Maximilian Dax · Chaithanya Kumar Mummadi · Nhung Ngo · Thi Hoai Phuong Nguyen · Zhongyu Lou · Thomas Brox -
2019 Poster: LCA: Loss Change Allocation for Neural Network Training »
Janice Lan · Rosanne Liu · Hattie Zhou · Jason Yosinski -
2019 Poster: Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask »
Hattie Zhou · Janice Lan · Rosanne Liu · Jason Yosinski -
2018 : Jason Yosinski, "Good and bad assumptions in model design and interpretability" »
Jason Yosinski -
2018 Poster: Faster Neural Networks Straight from JPEG »
Lionel Gueguen · Alex Sergeev · Ben Kadlec · Rosanne Liu · Jason Yosinski -
2018 Poster: An intriguing failing of convolutional neural networks and the CoordConv solution »
Rosanne Liu · Joel Lehman · Piero Molino · Felipe Petroski Such · Eric Frank · Alex Sergeev · Jason Yosinski -
2017 : Invited Talk 4 »
Anh Nguyen -
2017 Symposium: Interpretable Machine Learning »
Andrew Wilson · Jason Yosinski · Patrice Simard · Rich Caruana · William Herlands -
2017 Poster: SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability »
Maithra Raghu · Justin Gilmer · Jason Yosinski · Jascha Sohl-Dickstein -
2016 : Learning 3D representations, disparity estimation, and structure from motion »
Thomas Brox -
2016 Demonstration: Adventures with Deep Generator Networks »
Jason Yosinski · Anh Nguyen · Jeff Clune · Douglas K Bemis -
2016 Poster: Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images »
Vladimir Golkov · Marcin Skwark · Antonij Golkov · Alexey Dosovitskiy · Thomas Brox · Jens Meiler · Daniel Cremers -
2016 Oral: Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images »
Vladimir Golkov · Marcin Skwark · Antonij Golkov · Alexey Dosovitskiy · Thomas Brox · Jens Meiler · Daniel Cremers -
2016 Poster: Generating Images with Perceptual Similarity Metrics based on Deep Networks »
Alexey Dosovitskiy · Thomas Brox -
2014 Poster: Discriminative Unsupervised Feature Learning with Convolutional Neural Networks »
Alexey Dosovitskiy · Jost Tobias Springenberg · Martin Riedmiller · Thomas Brox -
2014 Poster: How transferable are features in deep neural networks? »
Jason Yosinski · Jeff Clune · Yoshua Bengio · Hod Lipson -
2014 Demonstration: Playing with Convnets »
Jason Yosinski · Hod Lipson -
2014 Oral: How transferable are features in deep neural networks? »
Jason Yosinski · Jeff Clune · Yoshua Bengio · Hod Lipson