- A Better Way to Pretrain Deep Boltzmann Machines. [url]
- A GeneratDeep neural networks for acoustic modeling in speech recognition: The shared views of four research groupsive Process for Sampling Contractive Auto-Encoders.[[pdf](docs/2012/A Generative Process for Sampling Contractive Auto-Encoders.pdf)] [url]
- An Efficient Learning Procedure for Deep Boltzmann Machines. [url]
- Autoencoders, Unsupervised Learning, and Deep Architectures. [url]
- Building High-level Features Using Large Scale Unsupervised Learning. [url]
- Deep Learning of Representations for Unsupervised and Transfer Learning. [url]
- Deep Learning via Semi-Supervised Embedding. [url]
- Deep Learning with Hierarchical Convolutional Factor Analysis. [url]
- Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups.[url] ⭐
- RDiscriminative Learning of Sum-Product Networks. [url]
- [AlexNet] ImageNet Classification with Deep Convolutional Neural Networks. [pdf] [code] [tensorflow]:star:
- [Dropout] Improving neural networks by preventing co-adaptation of feature detectors.
arxiv⭐ - Invariant Scattering Convolution Networks. [url]
- Learning with Hierarchical-Deep Models. [url]
- Practical Bayesian Optimization of Machine Learning Algorithms. [url] ⭐
- Practical Recommendations for Gradient-Based Training of Deep Architectures. [url]
- Random Search for Hyper-Parameter Optimization. [url] ⭐
- Cross-domain co-extraction of sentiment and topic lexicons. [pdf] ⭐
- Domain adaptation from multiple sources: a domain-dependent regularization approach. [pdf]
- Domain Transfer Multiple Kernel Learning. [pdf]
- Information-Theoretical Learning of Discriminative Clusters for Unsupervised Domain Adaptation. [pdf]
- Learning with Augmented Features for Heterogeneous Domain Adaptation. [pdf]
- Semi-Supervised Kernel Matching for Domain Adaptation. [pdf]
- Supplementary Material Geodesic Flow Kernel for Unsupervised Domain Adaptation. [pdf]
- TALMUD: transfer learning for multiple domains. [pdf]