Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis

no code implementations • 17 Jun 2022 • Shayegan Omidshafiei, Andrei Kapishnikov, Yannick Assogba, Lucas Dixon, Been Kim

Each year, expert-level performance is attained in increasingly-complex multiagent domains, where notable examples include Go, Poker, and StarCraft II.

Starcraft Starcraft II +1

IMACS: Image Model Attribution Comparison Summaries

no code implementations • 26 Jan 2022 • Eldon Schoop, Ben Wedin, Andrei Kapishnikov, Tolga Bolukbasi, Michael Terry

Developing a suitable Deep Neural Network (DNN) often requires significant iteration, where different model versions are evaluated and compared.

Image Classification

Acquisition of Chess Knowledge in AlphaZero

no code implementations • 17 Nov 2021 • Thomas McGrath, Andrei Kapishnikov, Nenad Tomašev, Adam Pearce, Demis Hassabis, Been Kim, Ulrich Paquet, Vladimir Kramnik

In this work we provide evidence that human knowledge is acquired by the AlphaZero neural network as it trains on the game of chess.

Game of Chess

Guided Integrated Gradients: An Adaptive Path Method for Removing Noise

1 code implementation • CVPR 2021 • Andrei Kapishnikov, Subhashini Venugopalan, Besim Avci, Ben Wedin, Michael Terry, Tolga Bolukbasi

To minimize the effect of this source of noise, we propose adapting the attribution path itself -- conditioning the path not just on the image but also on the model being explained.

XRAI: Better Attributions Through Regions

2 code implementations • ICCV 2019 • Andrei Kapishnikov, Tolga Bolukbasi, Fernanda Viégas, Michael Terry

Saliency methods can aid understanding of deep neural networks.