7.1k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- SupélecFR486 papers
- Shandong University of Political Science and LawCN485 papers
- Dalle Molle Institute for Artificial Intelligence ResearchCH65 papers
- New York UniversityUS52 papers
- Università della Svizzera italianaCH21 papers
- Google (United States)US16 papers
- Princeton UniversityUS15 papers
- Courant Institute of Mathematical SciencesUS13 papers
- Politecnico di TorinoIT12 papers
- Meta (Israel)IL11 papers
- Massachusetts Institute of TechnologyUS10 papers
- ETH ZurichCH9 papers
11 papers · 1 filter
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models
Juergen Schmidhuber
This paper addresses the general problem of reinforcement learning (RL) in partially observable environments. In 2013, our large RL recurrent neural networks (RNNs) learned from sc…
Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters
Jelena Luketina, Mathias Berglund, Klaus Greff +1
Hyperparameter selection generally relies on running multiple full training trials, with selection based on validation set performance. We propose a gradient-based approach for loc…
Surface growth for molten silicon infiltration into carbon millimeter-sized channels: Lattice-Boltzmann simulations, experiments and models
Danilo Sergi, Antonio Camarano, José Miguel Molina +2
The process of liquid silicon infiltration is investigated for channels with radii from to [mm] drilled in compact carbon preforms. The advantage of this setup is tha…
Training Very Deep Networks
Rupesh Kumar Srivastava, Klaus Greff, Jürgen Schmidhuber
Theoretical and empirical evidence indicates that the depth of neural networks is crucial for their success. However, training becomes more difficult as depth increases, and traini…
Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation
Marijn F. Stollenga, Wonmin Byeon, Marcus Liwicki +1
Convolutional Neural Networks (CNNs) can be shifted across 2D images or 3D videos to segment them. They have a fixed input size and typically perceive only small local contexts of…
Paneitz operator for metrics near
Fengbo Hang, Paul C. Yang
We derive the first and second variation formula for the Green's function pole's value of Paneitz operator on the standard three sphere. In particular it is shown that the first va…
3-D Statistical Channel Model for Millimeter-Wave Outdoor Mobile Broadband Communications
Mathew K. Samimi, Theodore S. Rappaport
This paper presents an omnidirectional spatial and temporal 3-dimensional statistical channel model for 28 GHz dense urban non-line of sight environments. The channel model is deve…
Exploiting Directionality for Millimeter-Wave Wireless System Improvement
George R. MacCartney, Mathew K. Samimi, Theodore S. Rappaport
This paper presents directional and omnidirectional RMS delay spread statistics obtained from 28 GHz and 73 GHz ultrawideband propagation measurements carried out in New York City…
LSTM: A Search Space Odyssey
Klaus Greff, Rupesh Kumar Srivastava, Jan Koutník +2
Several variants of the Long Short-Term Memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks hav…
The High-Mass Stellar Initial Mass Function in M31 Clusters
Daniel R. Weisz, L. Clifton Johnson, Daniel Foreman-Mackey +16
We have undertaken the largest systematic study of the high-mass stellar initial mass function (IMF) to date using the optical color-magnitude diagrams (CMDs) of 85 resolved, young…
A two-stage video coding framework with both self-adaptive redundant dictionary and adaptively orthonormalized DCT basis
Yuanyi Xue, Yi Zhou, Yao Wang
In this work, we propose a two-stage video coding framework, as an extension of our previous one-stage framework in [1]. The two-stage frameworks consists two different dictionarie…