before 2010
- A fast learning algorithm for deep belief nets. [url] :star:
- A Tutorial on Energy-Based Learning. [url]
- [LeNet] Gradient-based learning applied to document recognition. [pdf] :star:
- Constructing Informative Priors using Transfer Learning. [url]
- Connectionist Temporal Classification: Labelling unsegmented Sequence Data with Recurrent Neural Networks. [url]
- Deep Boltzmann Machines. [url] :star:
- Exploring Strategies for Training Deep Neural Networks. [url]
- Efficient Learning of Sparse Representations with an Energy-Based Model. [url] :star:
- Efficient sparse coding algorithms. [url] :star:
- Energy-Based Models in Document Recognition and Computer Vision. [url]
- Extracting and Composing Robust Features with Denoising Autoencoders. [url] :star:
- Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition. [url]
- Gaussian Process Models for Link Analysis and Transfer Learning. [url]
- Greedy Layer-Wise Training of Deep Networks. [url] :star:
- Learning Invariant Features through Topographic Filter Maps. [url]
- Linear Spatial Pyramid Matching Using Sparse Coding for Image Classification. [url] :star:
- Mapping and Revising Markov Logic Networks for Transfer Learning. [url]
- Nonlinear Learning using Local Coordinate Coding. [url] :star:
- Notes on Convolutional Neural Networks. [url]
- Reducing the Dimensionality of Data with Neural Networks. [science] :star:
- To Recognize Shapes, First Learn to Generate Images. [url]
- Scaling Learning Algorithms towards AI. [url] :star:
- Sparse deep belief net model for visual area V2. [url] :star:
- Sparse Feature Learning for Deep Belief Networks. [url]
- Training restricted Boltzmann machines using approximations to the likelihood gradient. [url]
- Training Products of experts by minimizing contrastive divergence</b>. [url]] :star:
- Using Fast Weights to Improve Persistent Contrastive Divergence. [url] :star:
- Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition. [url]
- What is the Best Multi-Stage Architecture for Object Recognition?. [url] :star:
Transfer learning
- A Survey on Transfer Learning. [url]] :star:
- Modeling Transfer Relationships Between Learning Tasks for Improved Inductive Transfer. [pdf]
- To Transfer or Not To Transfer.[url]
- Transfer learning for text classification. [url]
- Transfer learning for collaborative filtering via a rating-matrix generative model.[url]
- Transfer learning from multiple source domains via consensus regularization. [url]
- Transfer Learning for Reinforcement Learning Domains: A Survey. [url] :star:
- [Zero-Shot] Zero-Shot Learning with Semantic Output Codes.
pdf :star:
Instance transfer
- An improved categorization of classifier’s sensitivity on sample selection bias. [pdf]
- Boosting for transfer learning. [url] :star:
- A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. [pdf] :star:
- Correcting sample selection bias by unlabeled data. [pdf]
- Cross domain distribution adaptation via kernel mapping. [pdf]
- Direct Importance Estimation with Model Selection and Its Application to Covariate Shift Adaptation.[pdf]
- Discriminative learning for differing training and test distributions. [pdf]
- Domain Adaptation via Transfer Component Analysis. [pdf] :star:
- Instance Weighting for Domain Adaptation in NLP. [pdf]
- Logistic regression with an auxiliary data source. [pdf]
- Transferring Naive Bayes Classifiers for Text Classification. [pdf]
Feature representation transfer
- A Spectral Regularization Framework for Multi-Task Structure Learning. [pdf]
- Biographies, bollywood, boom- boxes and blenders: Domain adaptation for sentiment classification. [pdf]
- Co-clustering based Classification for Out-of-domain Documents. [pdf] :star:
- Domain adaptation with structural correspondence learning. [pdf]
- Frustratingly easy domain adaptation. [pdf] :star:
- Kernel-based inductive transfer. [pdf]
- Learning a meta-level prior for feature relevance from multiple related tasks. [pdf]
- Multi-task feature and kernel selection for svms. [pdf]
- Multi-task feature learning. [pdf] :star:
- Self-taught Clustering. [pdf]
- Self-taught Learning-Transfer Learning from Unlabeled Data. [url] :star:
- Spectral domain-transfer learning. [url] :star:
- Transfer learning via dimensionality reduction. [pdf]
Parameter transfer
- Knowledge transfer via multiple model local structure mapping. [pdf]
- Learning Gaussian Process Kernels via Hierarchical Bayes. [pdf]
- Learning to learn with the informative vector machine. [pdf]
- Multi-task Gaussian Process Prediction. [pdf]
- Regularized multi-task learning. [pdf]
- The more you know, the less you learn: from knowledge transfer to one-shot learning of object categories.[pdf]
Relational knowledge transfer
- Deep transfer via second-order markov logic. [pdf]
- Mapping and revising markov logic networks for transfer learning. [pdf]
- Transfer learning by mapping with minimal target data. [pdf]
- Translated learning: Transfer learning across different feature spaces.[url] :star: