“Reading Task”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
(相同用户的13个中间修订版本未显示)
第1行: 第1行:
  
{| class="wikitable" ! Affiliation !! Paper Name !!  Principal |-
+
{| class="wikitable"
||  || || |-
+
! Affiliation !! Paper Name !!  Principal !! Materials
| rowspan="3"| 2014/12/8 || rowspan='3'|Liu Rong || Yu Zhao, Zhiyuan Liu, Maosong Sun. Phrase Type Sensitive Tensor Indexing Model for Semantic Composition. AAAI'15. [http://nlp.csai.tsinghua.edu.cn/~lzy/publications/aaai2015_tim.pdf pdf]
+
 
|-
 
|-
| Yang Liu, Zhiyuan Liu, Tat-Seng Chua, Maosong Sun. Topical Word Embeddings. AAAI'15. [http://nlp.csai.tsinghua.edu.cn/~lzy/publications/aaai2015_twe.pdf pdf][https://github.com/largelymfs/topical_word_embeddings code]
 
|-
 
|  Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu. Learning Entity and Relation Embeddings for Knowledge Graph Completion. AAAI'15. [http://nlp.csai.tsinghua.edu.cn/~lzy/publications/aaai2015_transr.pdf pdf][https://github.com/mrlyk423/relation_extraction code]
 
  
 +
|align="center"| ICML 2015 ||align="center"| From Word Embeddings To Document Distances ||align="center" | - ||align="center" | -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Weight Uncertainty in Neural Network ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Long Short-Term Memory Over Recursive Structures ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Learning Transferable Features with Deep Adaptation Networks ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Learning Word Representations with Hierarchical Sparse Coding ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| DRAW: A Recurrent Neural Network For Image Generation ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Unsupervised Learning of Video Representations using LSTMs ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| MADE: Masked Autoencoder for Distribution Estimation ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Hashing for Distributed Data ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Is Feature Selection Secure against Training Data Poisoning? ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Mind the duality gap: safer rules for the Lasso ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| PeakSeg: constrained optimal segmentation and supervised penalty learning for peak detection in count data ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Generalization error bounds for learning to rank: Does the length of document lists matter? ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Classification with Low Rank and Missing Data ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Functional Subspace Clustering with Application to Time Series ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Abstraction Selection in Model-based Reinforcement Learning ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Learning Local Invariant Mahalanobis Distances ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| A Stochastic PCA and SVD Algorithm with an Exponential Convergence Rate ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Learning from Corrupted Binary Labels via Class-Probability Estimation ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| On the Relationship between Sum-Product Networks and Bayesian Networks ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Efficient Training of LDA on a GPU by Mean-for-Mode Estimation ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| A low variance consistent test of relative dependency ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Streaming Sparse Principal Component Analysis ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| How Can Deep Rectifier Networks Achieve Linear Separability and Preserve Distances? ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Online Learning of Eigenvectors ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Asymmetric Transfer Learning with Deep Gaussian Processes ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| BilBOWA: Fast Bilingual Distributed Representations without Word Alignments ||align="center"| Chao Xing ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Strongly Adaptive Online Learning ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Cascading Bandits: Learning to Rank in the Cascade Model ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Complex Event Detection using Semantic Saliency and Nearly-Isotonic SVM ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Latent Topic Networks: A Versatile Probabilistic Programming Framework for Topic Models ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Multi-Task Learning for Subspace Segmentation ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Convex Formulation for Learning from Positive and Unlabeled Data ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Alpha-Beta Divergences Discover Micro and Macro Structures in Data ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| On Greedy Maximization of Entropy ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| The Hedge Algorithm on a Continuum ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| MRA-based Statistical Learning from Incomplete Rankings ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| A Linear Dynamical System Model for Text ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| HawkesTopic: A Joint Model for Network Inference and Topic Modeling from Text-Based Cascades ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Support Matrix Machines ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Unsupervised Domain Adaptation by Backpropagation ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| The Ladder: A Reliable Leaderboard for Machine Learning Competitions ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| On Deep Multi-View Representation Learning ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| A Probabilistic Model for Dirty Multi-task Feature Selection ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICML 2015 ||align="center"| Deep Edge-Aware Filters ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| EMBEDDING ENTITIES AND RELATIONS FOR LEARNING AND INFERENCE IN KNOWLEDGE BASES.||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| TECHNIQUES FOR LEARNING BINARY STOCHASTIC FEEDFORWARD NEURAL NETWORKS.||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Joint RNN-Based Greedy Parsing and Word Composition ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Scheduled denoising autoencoders||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Adam: A Method for Stochastic Optimization||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Modeling Compositionality with Multiplicative Recurrent Neural Networks||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Explaining and Harnessing Adversarial Examples||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Deep Structured Output Learning for Unconstrained Text Recognition||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Zero-bias autoencoders and the benefits of co-adapting features||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Understanding Locally Competitive Networks||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Leveraging Monolingual Data for Crosslingual Compositional Word Representations||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Word Representations via Gaussian Embedding||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Qualitatively characterizing neural network optimization problems||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Memory Networks||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Generative Modeling of Convolutional Neural Networks||align="center"| ChaoYuan Zuo ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| A Unified Perspective on Multi-Domain and Multi-Task Learning||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Learning Non-deterministic Representations with Energy-based Ensembles||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Diverse Embedding Neural Network Language Models||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Hot Swapping for Online Adaptation of Optimization Hyperparameters ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Representation Learning for cold-start recommendation||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| On the Stability of Deep Networks||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Stochastic Descent Analysis of Representation Learning Algorithms||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Deep metric learning using Triplet network ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Learning Longer Memory in Recurrent Neural Networks||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Inducing Semantic Representation from Text by Jointly Predicting and Factorizing Relations ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| NICE: Non-linear Independent Components Estimation ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Tailoring Word Embeddings for Bilexical Predictions: An Experimental Comparison ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| On Learning Vector Representations in Hierarchical Label Spaces||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Real-World Font Recognition Using Deep Network and Domain Adaptation||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Algorithmic Robustness for Learning via (ε,γ,τ)-Good Similarity Functions||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Score Function Features for Discriminative Learning ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Parallel training of DNNs with Natural Gradient and Parameter Averaging||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| A Generative Model for Deep Convolutional Learning ||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Random Forests Can Hash||align="center"| - ||align="center"| -
 +
|-
 +
|align="center"| ICLR 2015 ||align="center"| Provable Methods for Training Neural Networks with Sparse Connectivity ||align="center"| - ||align="center"| -
 
|-
 
|-
|2015/07/10 ||Liu Rong||  
+
|align="center"| ICLR 2015 ||align="center"| Deep learning with Elastic Averaging SGD ||align="center"| - ||align="center"| -  
*Context-Dependent Translation Selection Using Convolutional Neural Network [http://arxiv.org/abs/1503.02357]
+
*Syntax-based Deep Matching of Short Texts [http://arxiv.org/abs/1503.02427]
+
*Convolutional Neural Network Architectures for Matching Natural Language Sentences[http://www.hangli-hl.com/uploads/3/1/6/8/3168008/hu-etal-nips2014.pdf]
+
*LSTM: A Search Space Odyssey [http://arxiv.org/pdf/1503.04069.pdf]
+
*A Deep Embedding Model for Co-occurrence Learning  [http://arxiv.org/abs/1504.02824]
+
*Text segmentation based on semantic word embeddings[http://arxiv.org/abs/1503.05543]
+
*semantic parsing via paraphrashings[http://www.cs.tau.ac.il/research/jonathan.berant/homepage_files/publications/ACL14.pdf]
+
 
|-
 
|-
 +
|align="center"| ICLR 2015 ||align="center"| Example Selection For Dictionary Learning ||align="center"| - ||align="center"| -
 
|-
 
|-
|2015/07/22 ||Dong Wang||
+
|align="center"| ICLR 2015 ||align="center"| Unsupervised Domain Adaptation with Feature Embeddings ||align="center"| - ||align="center"| -
*From Word Embeddings To Document Distances [http://jmlr.org/proceedings/papers/v37/kusnerb15.pdf pdf]
+
*[[Asr-read-icml|Reading list for ICML2015]]
+
 
|-
 
|-
 
|}
 
|}

2015年7月27日 (一) 14:17的最后版本

Affiliation Paper Name Principal Materials
ICML 2015 From Word Embeddings To Document Distances - -
ICML 2015 Weight Uncertainty in Neural Network - -
ICML 2015 Long Short-Term Memory Over Recursive Structures - -
ICML 2015 Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift - -
ICML 2015 Learning Transferable Features with Deep Adaptation Networks - -
ICML 2015 Learning Word Representations with Hierarchical Sparse Coding - -
ICML 2015 DRAW: A Recurrent Neural Network For Image Generation - -
ICML 2015 Unsupervised Learning of Video Representations using LSTMs - -
ICML 2015 MADE: Masked Autoencoder for Distribution Estimation - -
ICML 2015 Hashing for Distributed Data - -
ICML 2015 Is Feature Selection Secure against Training Data Poisoning? - -
ICML 2015 Mind the duality gap: safer rules for the Lasso - -
ICML 2015 PeakSeg: constrained optimal segmentation and supervised penalty learning for peak detection in count data - -
ICML 2015 Generalization error bounds for learning to rank: Does the length of document lists matter? - -
ICML 2015 Classification with Low Rank and Missing Data - -
ICML 2015 Functional Subspace Clustering with Application to Time Series - -
ICML 2015 Abstraction Selection in Model-based Reinforcement Learning - -
ICML 2015 Learning Local Invariant Mahalanobis Distances - -
ICML 2015 A Stochastic PCA and SVD Algorithm with an Exponential Convergence Rate - -
ICML 2015 Learning from Corrupted Binary Labels via Class-Probability Estimation - -
ICML 2015 On the Relationship between Sum-Product Networks and Bayesian Networks - -
ICML 2015 Efficient Training of LDA on a GPU by Mean-for-Mode Estimation - -
ICML 2015 A low variance consistent test of relative dependency - -
ICML 2015 Streaming Sparse Principal Component Analysis - -
ICML 2015 How Can Deep Rectifier Networks Achieve Linear Separability and Preserve Distances? - -
ICML 2015 Online Learning of Eigenvectors - -
ICML 2015 Asymmetric Transfer Learning with Deep Gaussian Processes - -
ICML 2015 Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network - -
ICML 2015 BilBOWA: Fast Bilingual Distributed Representations without Word Alignments Chao Xing -
ICML 2015 Strongly Adaptive Online Learning - -
ICML 2015 Cascading Bandits: Learning to Rank in the Cascade Model - -
ICML 2015 Complex Event Detection using Semantic Saliency and Nearly-Isotonic SVM - -
ICML 2015 Latent Topic Networks: A Versatile Probabilistic Programming Framework for Topic Models - -
ICML 2015 Multi-Task Learning for Subspace Segmentation - -
ICML 2015 Convex Formulation for Learning from Positive and Unlabeled Data - -
ICML 2015 Alpha-Beta Divergences Discover Micro and Macro Structures in Data - -
ICML 2015 On Greedy Maximization of Entropy - -
ICML 2015 The Hedge Algorithm on a Continuum - -
ICML 2015 MRA-based Statistical Learning from Incomplete Rankings - -
ICML 2015 A Linear Dynamical System Model for Text - -
ICML 2015 HawkesTopic: A Joint Model for Network Inference and Topic Modeling from Text-Based Cascades - -
ICML 2015 Support Matrix Machines - -
ICML 2015 Unsupervised Domain Adaptation by Backpropagation - -
ICML 2015 The Ladder: A Reliable Leaderboard for Machine Learning Competitions - -
ICML 2015 On Deep Multi-View Representation Learning - -
ICML 2015 A Probabilistic Model for Dirty Multi-task Feature Selection - -
ICML 2015 Deep Edge-Aware Filters - -
ICLR 2015 EMBEDDING ENTITIES AND RELATIONS FOR LEARNING AND INFERENCE IN KNOWLEDGE BASES. - -
ICLR 2015 TECHNIQUES FOR LEARNING BINARY STOCHASTIC FEEDFORWARD NEURAL NETWORKS. - -
ICLR 2015 Joint RNN-Based Greedy Parsing and Word Composition - -
ICLR 2015 Scheduled denoising autoencoders - -
ICLR 2015 Adam: A Method for Stochastic Optimization - -
ICLR 2015 Modeling Compositionality with Multiplicative Recurrent Neural Networks - -
ICLR 2015 Explaining and Harnessing Adversarial Examples - -
ICLR 2015 Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition - -
ICLR 2015 Deep Structured Output Learning for Unconstrained Text Recognition - -
ICLR 2015 Zero-bias autoencoders and the benefits of co-adapting features - -
ICLR 2015 Understanding Locally Competitive Networks - -
ICLR 2015 Leveraging Monolingual Data for Crosslingual Compositional Word Representations - -
ICLR 2015 Word Representations via Gaussian Embedding - -
ICLR 2015 Qualitatively characterizing neural network optimization problems - -
ICLR 2015 Memory Networks - -
ICLR 2015 Generative Modeling of Convolutional Neural Networks ChaoYuan Zuo -
ICLR 2015 A Unified Perspective on Multi-Domain and Multi-Task Learning - -
ICLR 2015 Learning Non-deterministic Representations with Energy-based Ensembles - -
ICLR 2015 Diverse Embedding Neural Network Language Models - -
ICLR 2015 Hot Swapping for Online Adaptation of Optimization Hyperparameters - -
ICLR 2015 Representation Learning for cold-start recommendation - -
ICLR 2015 On the Stability of Deep Networks - -
ICLR 2015 Stochastic Descent Analysis of Representation Learning Algorithms - -
ICLR 2015 Deep metric learning using Triplet network - -
ICLR 2015 Learning Longer Memory in Recurrent Neural Networks - -
ICLR 2015 Inducing Semantic Representation from Text by Jointly Predicting and Factorizing Relations - -
ICLR 2015 NICE: Non-linear Independent Components Estimation - -
ICLR 2015 Tailoring Word Embeddings for Bilexical Predictions: An Experimental Comparison - -
ICLR 2015 On Learning Vector Representations in Hierarchical Label Spaces - -
ICLR 2015 Real-World Font Recognition Using Deep Network and Domain Adaptation - -
ICLR 2015 Algorithmic Robustness for Learning via (ε,γ,τ)-Good Similarity Functions - -
ICLR 2015 Score Function Features for Discriminative Learning - -
ICLR 2015 Parallel training of DNNs with Natural Gradient and Parameter Averaging - -
ICLR 2015 A Generative Model for Deep Convolutional Learning - -
ICLR 2015 Random Forests Can Hash - -
ICLR 2015 Provable Methods for Training Neural Networks with Sparse Connectivity - -
ICLR 2015 Deep learning with Elastic Averaging SGD - -
ICLR 2015 Example Selection For Dictionary Learning - -
ICLR 2015 Unsupervised Domain Adaptation with Feature Embeddings - -