2011
Deep Learning
- Adaptive Deconvolutional Networks for Mid and High Level Feature Learning. [url]
- Asymptotic efficiency of deterministic estimators for discrete energy-based models Ratio matching and pseudolikelihood. [url]
- Building high-level features using large scale unsupervised learning.
arxiv
- Contractive Auto-Encoders-Explicit Invariance During Feature Extraction. [url]
- Cross-domain activity recognition via transfer learning. [url]
- Heterogeneous Transfer Learning for Image Classification. [url] :star:
- Kinship Verification through Transfer Learning. [url]
- Learning Deep Energy Models. [url]
- Learning image representations from the pixel level via hierarchical sparse coding. [url]
- Natural Language Processing (almost) from Scratch. [url] :star:
- On Autoencoders and Score Matching for Energy Based Models. [url]
- On Optimization Methods for Deep Learning. [url]
- On the Expressive Power of Deep Architectures. [url]
- Spike-and-Slab Sparse Coding for Unsupervised Feature Discovery. [url]
- Unsupervised Learning of Hierarchical Representations with Convolutional Deep Belief Networks. [url]]
- Unsupervised Models of Images by Spike-and-Slab RBMs. [url]
Attention
- Learning where to Attend with Deep Architectures for Image Tracking.
arxiv
Transfer learning
- Domain Adaptation for Large-Scale Sentiment Classification - A Deep Learning Approach. [pdf] :star:
- Heterogeneous domain adaptation using manifold alignment. [pdf]
- Heterogeneous Transfer Learning for Image Classification. [pdf] [code]
- Learning from multiple outlooks. [pdf]
- Multi-source domain adaptation and its application to early detection of fatigue. [pdf] :star:
- What you saw is not what you get: Domain adaptation using asymmetric kernel transforms. [pdf]