Memory Network:

Most referenced

1. Memory Networks,

2. End-To-End Memory Networks,

3. Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks,

4. Large-scale Simple Question Answering with Memory Networks,

5. Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems,

6. The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations,

7. Learning End-to-End Goal-Oriented Dialog,

ICML2016

1. Ask Me Anything: Dynamic Memory Networks for Natural Language Processing, 1

2. Meta-Learning with Memory-Augmented Neural Networks,

3. Associative Long Short-Term Memory,

4. Recurrent Orthogonal Networks and Long-Memory Tasks,

5. Dynamic Memory Networks for Visual and Textual Question Answering,

6. Control of Memory, Active Perception, and Action in Minecraft,

One Shot

CVPR16

1. One-Shot Learning of Scene Locations via Feature Trajectory Transfer,

ICML16

1. One-Shot Generalization in Deep Generative Models,

Zero Shot

CVPR16

1. Multi-Cue Zero-Shot Learning With Strong Supervision,

2. Latent Embeddings for Zero-Shot Classification,

3. Less Is More: Zero-Shot Learning From Online Textual Documents With Noise Suppression,

4. Synthesized Classifiers for Zero-Shot Learning,

5. Fast Zero-Shot Image Tagging,

6. Zero-Shot Learning via Joint Latent Similarity Embedding,

Unsupervised

Most referenced

1. Unsupervised Learning of Video Representations using LSTMs,

2. Unsupervised Representation Learning With Deep Convolutional Generative Adversarial Networks,

ICML2016

1. A Deep Learning Approach to Unsupervised Ensemble Learning,

2. Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification,

3. Unsupervised Deep Embedding for Clustering Analysis,

CVPR2016

1. Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks,

2. Joint Unsupervised Learning of Deep Representations and Image Clusters,

Semi/Weakly-supervised

Most referenced

1. Semi-supervised Sequence Learning,

2. Semi-supervised Learning with Deep Generative Models,

ICML2016

1. Weakly- and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation,

CVPR2016

1. NetVLAD: CNN architecture for weakly supervised place recognition,

2. Weakly Supervised Deep Detection Networks,

3. WELDON: Weakly Supervised Learning of Deep Convolutional Neural

   Networks,

4. Weakly Supervised Object Boundaries,

5. Deep Hand: How to Train a CNN on 1 Million Hand Images When Your Data Is Continuous and Weakly Labelled