On the Dimensionality of Word Embedding
WHY?
Dimension of word embedding is usually determined with heuristic.
Inferring and Executing Programs for Visual Reasoning
in Studies on Deep Learning, Computer Vision
WHY?
Neural modular networks do not generalize well to new questions since their performance rely on syntactic parser.
Deep Compositional Question Answering with Neural Module Networks
in Studies on Deep Learning, Computer Vision
WHY?
Visual question answering task is compositional in nature.
Tracking Emerges by Colorizing Videos
in Studies on Deep Learning, Computer Vision
WHY?
Segmenting objects in videos is difficult without manual labels.
Latent Alignment and Variational Attention
in Studies on Deep Learning, Deep Learning
WHY?
Even though attention is being widely used, it is hard to be considered as probabilistic model as the attention does not marginalize.
FiLM: Visual Reasoning with a General Conditioning Layer
in Studies on Deep Learning, Computer Vision
WHY?
There are some architectures for relational reasoning but lacks general-purpose components for relational reasoning and visual question answering.
TasNet: Time-Domain Audio Separation Network for Real-Time Single-channel Speech Separation
in Studies on Deep Learning, Audio
WHY?
Separating multiple sources of audio is difficult task. Previous works mostly made mask for each source in time-fequency domain.
Recurrent Relational Networks
in Studies on Deep Learning, Deep Learning
WHY?
Some tasks such as Sudoku require serial steps of relational inference.
