Graph-Sparse LDA uses ontology-guided sparsity, compressing an ASD topic from 119 diagnoses to 6 concepts without losing predictive performance.

Finale Doshi-Velez, Byron Wallace, Ryan Adams

Memory Networks integrate inference and long-term memory to enhance QA task performance.

Jason Weston, Sumit Chopra, Antoine Bordes

This paper analyzes the computational complexity of training neural networks, showing over-parameterized networks are easier to optimize and proposing polynomial activation-based algorithms for depth-2 and depth-3 networks.

Roi Livni, Shai Shalev-Shwartz, Ohad Shamir

Proposes a gradient reversal-based unsupervised domain adaptation method, significantly improving cross-domain image classification accuracy.

Yaroslav Ganin, Victor Lempitsky

Proposed Inception architecture employs multi-scale convolutions and dimension reduction, achieving 28.6% Top-5 error on ImageNet with 1/12 parameters of AlexNet.

Christian Szegedy, Wei Liu, Yangqing Jia et al.

Proposes a deep multi-layer LSTM-based end-to-end sequence-to-sequence model achieving BLEU 34.8 on WMT'14 English-French translation, outperforming phrase-based SMT.

Ilya Sutskever, Oriol Vinyals, Quoc V. Le

Using atomic frequency comb protocol in a 20-meter erbium-doped fiber, this work demonstrates 1532 nm photon storage with high fidelity and preserved entanglement.

Erhan Saglamyurek, Jeongwan Jin, Varun B. Verma et al.

Deep CNNs like AlexNet, VGG, ResNet trained on 14 million images achieved top-5 error rates below 7%, revolutionizing large-scale image recognition.

Olga Russakovsky, Jia Deng, Hao Su et al.

Introduces a neural machine translation model with joint alignment and translation via attention, achieving BLEU 28.45 on WMT’14 English-French.

Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio

Proposes an Extended Dynamic Mode Decomposition (EDMD) to approximate Koopman eigenvalues, eigenfunctions, and modes from data, with proven convergence to Galerkin methods.

Matthew O. Williams, Ioannis G. Kevrekidis, Clarence W. Rowley

Introduces SimLex-999, a gold standard for semantic similarity, covering multiple POS and abstract/concrete concepts, outperforming WordSim-353 and MEN.

Felix Hill, Roi Reichart, Anna Korhonen

Framework for statistical guarantees of EM and gradient EM, combining population and finite-sample analysis.

Sivaraman Balakrishnan, Martin J. Wainwright, Bin Yu

The paper proposes Bandit algorithms for tree search, improving the over-optimism issue of the UCT algorithm.

Pierre-Arnuad Coquelin, Remi Munos

EAGLE employs a novel thermal feedback model calibrated to match the z≈0 galaxy stellar mass function with 0.2dex accuracy, enabling realistic galaxy formation simulations.

Joop Schaye, Robert A. Crain, Richard G. Bower et al.

Introduces 'Intelligent Trial and Error' algorithm enabling robots to adapt within 2 minutes post-damage, mimicking animal repair behaviors.

Antoine Cully, Jeff Clune, Danesh Tarapore et al.

Motility-induced phase separation (MIPS) arises from the coupling between particle speed and local density, revealing a non-equilibrium phase behavior in active matter.

Michael E. Cates, Julien Tailleur

Introduces Predictive Entropy Search (PES) for efficient black-box function optimization.

José Miguel Hernández-Lobato, Matthew W. Hoffman, Zoubin Ghahramani

clingo 4 integrates ASP with scripting control, enabling complex, dynamic reasoning processes.

Martin Gebser, Roland Kaminski, Benjamin Kaufmann et al.

MS COCO dataset with 91 categories, 2.5 million instances, enhances scene understanding and precise localization.

Tsung-Yi Lin, Michael Maire, Serge Belongie et al.

Proposes a hybrid data-model parallel training method for CNNs, achieving over 6x speedup on 8 GPUs with minimal accuracy loss.

Alex Krizhevsky