These are the posters that caught my eye on the third day of NIPS. Note that they are HDR images, so zoom in using your computer to see more detail. Some of the posters below have extra images focusing on specific parts of the poster to give more visual detail.

• Action-Conditional Video Prediction using Deep Networks in Atari Games, poster images: 1
• Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation: 1
• On-the-Job Learning with Bayesian Decision Theory: 1
• Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding: 1
• Backpropagation for Energy-Efficient Neuromorphic Computing: 1, 2, 3, 4, 5
• Attention-Based Models for Speech Recognition: 1
• Spatial Transformer Networks: 1, 2, 3, 4
• Where are they looking? 1, 2, 3, 4
• Learning Wake-Sleep Recurrent Visual Attention Models: 1, 2, 3, 4

Subscribe to my RSS feed and follow me on Twitter to stay up to date on new posts.

Please note that this is my personal blog — the views expressed on these pages are mine alone and not those of my employer.