Learning by Abstraction: The Neural State Machine
On calibration of modern neural networks
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Provisional Year presentation practice
Combining Search, Social Media, and Traditional Data Sources to Improve Influenza Surveillance
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
Jiayuan Mao, Chuang Gan, Pushmeet Kohli, Joshua B. Tenenbaum, Jiajun Wu
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Neural Decipherment via Minimum-Cost Flow: from Ugaritic to Linear B
Jiaming Luo Yuan Cao Regina Barzilay
AN EMPIRICAL STUDY OF EXAMPLE FORGETTING DURING DEEP NEURAL NETWORK LEARNING
Densely Connected Convolutional Networks
Toward an AI Physicist for Unsupervised Learning
Fake news detection in social networks via crowd signals.
Tschiatschek, Sebastian, Adish Singla, Manuel Gomez Rodriguez, Arpit Merchant, and Andreas Krause.
In Companion of the The Web Conference 2018 on The Web Conference 2018, pp. 517-524. International World Wide Web Conferences Steering Committee, 2018.
Controlling an organic synthesis robot with machine learning to search for new reactivity
Jarosław M. Granda, Liva Donina, Vincenza Dragone, De-Liang Long & Leroy Cronin
Nature volume 559, pages377–381 (2018)
A Brief Survey of Deep Reinforcement Learning
Should computers run the world?
IMAGENET-TRAINED CNNS ARE BIASED TOWARDS TEXTURE; INCREASING SHAPE BIAS IMPROVES ACCURACY AND ROBUSTNESS
K. O. Stanley and R. Miikkulainen, “Evolving Neural Networks through Augmenting Topologies,” Evolutionary Computation, vol. 10, no. 2, pp. 99–127, Jun. 2002.