- A Connection Between Score Matching and Denoising Autoencoders. [url]
- Attribute-Based Transfer Learning for Object Categorization with Zero/One Training Example. [url]
- A Practical Guide to Training Restricted Boltzmann Machines. [url] ⭐
- A Theoretical Analysis of Feature Pooling in Visual Recognition. [url]
- Convolutional Networks and Applications in Vision. [url]
- [DeepBigSimpleNet] Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition.
arxiv⭐ - Deep learning via Hessian-free optimization. [url]
- Efficient Learning of Deep Boltzmann Machines. [url]
- Image Classification using Super-Vector Coding of Local Image Descriptors. [url]
- Learning Convolutional Feature Hierarchies for Visual Recognition. [url]
- Learning Deep Architectures for AI. [url] ⭐
- Learning Mid-Level Features For Recognition. [url] ⭐
- Learning Restricted Boltzmann Machines using Mode-Hopping MCMC. [url] ⭐
- Locality-constrained Linear Coding for Image Classification.[url] ⭐
- Modeling Pixel Means and Covariances Using Factorized Third-Order Boltzmann Machines. [url]
- On the Convergence Properties of Contrastive Divergence. [url]
- Regularized estimation of image statistics by Score Matching. [url]
- Stacked Denoising Autoencoders Learning Useful Representations in a Deep Network with a Local Denoising Criterion. [remote url] ⭐
- Why Does Unsupervised Pre-training Help Deep Learning?. [url] ⭐
- Hierarchical Reinforcement Learning for Adaptive Text Generation. [pdf]
- Boosting for transfer learning with multiple sources. [pdf]
- Bregman Divergence-Based Regularization for Transfer Subspace Learning. [pdf]
- Cross-Domain Sentiment Classification via Spectral Feature Alignment. [pdf] ⭐
- Safety in numbers: Learning categories from few examples with multi model knowledge transfer. [pdf] ⭐
- Transfer Learning in Collaborative Filtering for Sparsity Reduction.[url]
- Transfer Learning for Collective Link Prediction in Multiple Heterogenous Domains. [url]
- Transfer Learning on Heterogenous Feature Spaces via Spectral Transformation. [pdf]