覚え書きブログ

読者です 読者をやめる 読者になる 読者になる

NIPS2014でDeep Learningに関連しそうな論文の一覧

ディープラーニング

機械学習のトップレベルの国際会議NIPS(Neural Information Processing Systems)が、2014年12月8日から11日まで、カナダのモントリオールで開催される。NIPSは、「Neural」という単語から始まるだけあって、昨今何かと話題のDeep Learningに関連の論文が多い。以下、Deep Learningに関連する論文を挙げてみた。

M50: An Autoencoder Approach to Learning Bilingual Word Representations
http://papers.nips.cc/paper/5270-an-autoencoder-approach-to-learning-bilingual-word-representations

M51: Pre-training of Recurrent Neural Networks via Linear Autoencoders
http://papers.nips.cc/paper/5271-pre-training-of-recurrent-neural-networks-via-linear-autoencoders

M52: Using Convolutional Neural Networks to Recognize Rhythm Stimuli from Electroencephalography Recordings
http://papers.nips.cc/paper/5272-using-convolutional-neural-networks-to-recognize-rhythm-stimuli-from-electroencephalography-recordings

M55: Global Belief Recursive Neural Networks
http://papers.nips.cc/paper/5275-global-belief-recursive-neural-networks

M56: Deep Networks with Internal Selective Attention through Feedback Connections
http://papers.nips.cc/paper/5276-deep-networks-with-internal-selective-attention-through-feedback-connections

M58: General Stochastic Networks for Classification
http://papers.nips.cc/paper/5278-general-stochastic-networks-for-classification

M:59: Improved Multimodal Deep Learning with Variation of Information
http://papers.nips.cc/paper/5279-improved-multimodal-deep-learning-with-variation-of-information

M60: Restricted Boltzmann machines modeling human choice
http://papers.nips.cc/paper/5280-restricted-boltzmann-machines-modeling-human-choice

M61: Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
http://papers.nips.cc/paper/5281-deep-fragment-embeddings-for-bidirectional-image-sentence-mapping

T87: Deep Learning Face Representation by Joint Identification-Verification
http://papers.nips.cc/paper/5416-deep-learning-face-representation-by-joint-identification-verification

T91: Learning Deep Features for Scene Recognition using Places Database
http://papers.nips.cc/paper/5349-learning-deep-features-for-scene-recognition-using-places-database

T92: Do Convnets Learn Correspondence?
http://papers.nips.cc/paper/5420-do-convnets-learn-correspondence

T93: Semi-supervised Learning with Deep Generative Models
http://papers.nips.cc/paper/5352-semi-supervised-learning-with-deep-generative-models

T94: Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning
http://papers.nips.cc/paper/5421-deep-learning-for-real-time-atari-game-play-using-offline-monte-carlo-tree-search-planning

T95: On the Number of Linear Regions of Deep Neural Networks
http://papers.nips.cc/paper/5422-on-the-number-of-linear-regions-of-deep-neural-networks

T96: Generative Adversarial Nets
http://papers.nips.cc/paper/5423-generative-adversarial-nets

T97: Deep Symmetry Networks
http://papers.nips.cc/paper/5424-deep-symmetry-networks

T98: Sequence to Sequence Learning with Neural Networks
http://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks

T99: Two-Stream Convolutional Networks for Action Recognition in Videos
http://papers.nips.cc/paper/5353-two-stream-convolutional-networks-for-action-recognition-in-videos

W36: Do Deep Nets Really Need to be Deep?
http://papers.nips.cc/paper/5484-do-deep-nets-really-need-to-be-deep

W37: How transferable are features in deep neural networks?
http://papers.nips.cc/paper/5347-how-transferable-are-features-in-deep-neural-networks

W38: Deep Convolutional Neural Network for Image Deconvolution
http://papers.nips.cc/paper/5485-deep-convolutional-neural-network-for-image-deconvolution

W55: Convex Deep Learning via Normalized Kernels
http://papers.nips.cc/paper/5496-convex-deep-learning-via-normalized-kernels

W66: Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics
http://papers.nips.cc/paper/5444-learning-neural-network-policies-with-guided-policy-search-under-unknown-dynamics

W86: Multi-Class Deep Boosting
http://papers.nips.cc/paper/5514-multi-class-deep-boosting

Th1: Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
http://papers.nips.cc/paper/5544-exploiting-linear-structure-within-convolutional-networks-for-efficient-evaluation

Th2: Unsupervised Deep Haar Scattering on Graphs
http://papers.nips.cc/paper/5545-unsupervised-deep-haar-scattering-on-graphs

Th3: Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations
http://papers.nips.cc/paper/5546-multi-view-perceptron-a-deep-model-for-learning-face-identity-and-view-representations

Th4: Deep Joint Task Learning for Generic Object Extraction
http://papers.nips.cc/paper/5547-deep-joint-task-learning-for-generic-object-extraction

Th5: Discriminative Unsupervised Feature Learning with Convolutional Neural Networks
http://papers.nips.cc/paper/5548-discriminative-unsupervised-feature-learning-with-convolutional-neural-networks

Th6: Modeling Deep Temporal Dependencies with Recurrent Grammar Cells""
http://papers.nips.cc/paper/5549-modeling-deep-temporal-dependencies-with-recurrent-grammar-cells

Th7: Convolutional Neural Network Architectures for Matching Natural Language Sentences
http://papers.nips.cc/paper/5550-convolutional-neural-network-architectures-for-matching-natural-language-sentences

Th8: Deep Recursive Neural Networks for Compositionality in Language
http://papers.nips.cc/paper/5551-deep-recursive-neural-networks-for-compositionality-in-language

多少の漏れがあるかもしれないが、これでもかなり多い。さらには、ワークショップ(Deep Learning and Representation Learning)も開催される。
https://nips.cc/Conferences/2014/Program/event.php?ID=4294