papers.md

Applications

Architectures

RNN's

Theory, Reasoning, Memory etc

Saliency

• NUS: Deep Learning for Saliency
• Saliency Detection by Multi-Context Deep Learning
• Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images

Visualization

• Deep Inside Convolutional Networks: Visualizing Image Classification Models and Saliency Maps

Deeper Architectures

• Deep Residual Learning for Image Recognition

Shallow Architectures

• Highway Networks

Misc

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Context

• A Critical View of Context: Not Deep Learning

Suggestions

• Next Week

  • [Res Net]
  • [NiN]
  • Lightning Talks
    • Inception 2, Inception3, Inception 4 [15 mins]
    • Xavier [10 mins]
    • ELu [4 mins]
    • PreLU [10 mins]
    • VReLU [5 mins]
    • Dilated Conv: Multiplescale Context Aggregration using [5 mins]
    • CNN features of the off-the shelf: an Astounding Baseline

• Week After

  • [STN]
  • [Sim Nets]
  • [Siamese ]

• [RL using OpenAI]: Weekend Hacknight

• [Generative Algo]

  • Suraj: Generative Adverserial Networks
  • Variational Autoencoders

• [ ]

• []