### Deep Learning

- DragoNN.
- The unreasonable effectiveness of Character-level Language Models (and why RNNs are still cool)
- The Unreasonable Effectiveness of Recurrent Neural Networks
A Learned Representation For Artistic Style. arXiv:1610.07629.

Why does deep and cheap learning work so well?. arXiv:1608.08225.

X Zhang, J Zhao, Y LeCun. Character-level Convolutional Networks for Text Classification. NIPS 2015.

*Paragraph Vector*

- QV Le, T Mikolov. Distributed Representations of Sentences and Documents.

- Recurrent Neural Networks for Spatiotemporal Dynamics of Intrinsic Networks from fMRI Data. arXiv:1611.00864.
- Towards end-to-end optimisation of functional image analysis pipelines. arXiv:1610.04079.
- Mapping Between Natural Movie fMRI Responses and Word-Sequence Representations. arXiv:1610.03914.

#### Network Representation Learning

- struc2vec: Learning Node Representations from Structural Identity. arXiv:1704.03165.
- From Node Embedding To Community Embedding. arXiv:1610.09950.
- node2vec: Scalable Feature Learning for Networks. KDD 2016.
- B Perozzi, R Al-Rfou, S Skiena. DeepWalk: online learning of social representations. KDD 2014.