Sciweavers

AAAI
2015
10 years 1 months ago
Active Advice Seeking for Inverse Reinforcement Learning
Intelligent systems that interact with humans typically require input in the form of demonstrations and/or advice for optimal decision making. In more traditional systems, such in...
Phillip Odom, Sriraam Natarajan
AAAI
2015
10 years 1 months ago
Kickback Cuts Backprop's Red-Tape: Biologically Plausible Credit Assignment in Neural Networks
Error backpropagation is an extremely effective algorithm for assigning credit in artificial neural networks. However, weight updates under Backprop depend on lengthy recursive c...
David Balduzzi, Hastagiri Vanchinathan, Joachim M....
AAAI
2015
10 years 1 months ago
Learning Large-Scale Dynamic Discrete Choice Models of Spatio-Temporal Preferences with Application to Migratory Pastoralism in
Understanding spatio-temporal resource preferences is paramount in the design of policies for sustainable development. Unfortunately, resource preferences are often unknown to pol...
Stefano Ermon, Yexiang Xue, Russell Toth, Bistra N...
96
Voted
AAAI
2015
10 years 1 months ago
Learning to Uncover Deep Musical Structure
The overarching goal of music theory is to explain the inner workings of a musical composition by examining the structure of the composition. Schenkerian music theory supposes tha...
Phillip B. Kirlin, David Jensen
118
Voted
AAAI
2015
10 years 1 months ago
Using Machine Teaching to Identify Optimal Training-Set Attacks on Machine Learners
We investigate a problem at the intersection of machine learning and security: training-set attacks on machine learners. In such attacks an attacker contaminates the training data...
Shike Mei, Xiaojin Zhu