Neural Arithmetic Logit Units
in Studies on Deep Learning, Deep Learning
WHY?
Neural network was poor at manipulating numerical information outside the range of training set.
VAE with a VampPrior
WHY?
Choosing an appropriate prior is important for VAE. This paper suggests two-layered VAE with flexible VampPrior.
Large Scale GAN Training for High Fidelity Natural Image Synthesis
WHY?
Generating a high resolution image with GAN is difficult despite of recent advances. This paper suggests BigGAN which adds few tricks on previous model to generate large scale images without progressively growing the network.
Bilinear Attention Networks
in Studies on Deep Learning, Computer Vision
WHY?
Representing bilinear relationship of two inputs is expensive. MLB efficiently reduced the number of parameters by substituting bilinear operation with Hadamard product operation. This paper extends this idea to capture bilinear attention between two multi-channel inputs.
Hybrid computing using a neural network with dynamic external memory
in Studies on Deep Learning, Deep Learning
WHY?
Using external memory as modern computer enable neural net the use of extensible memory. This paper suggests Differentible Neural Computer(DNC) which is an advanced version of Neural Turing Machine.
SSD: Single Shot MultiBox Detector
in Studies on Deep Learning, Computer Vision
WHY?
Object box proposal process is complicated and slow in object detection process. This paper proposes Single Shot Detector(SSD) to detect objects with single neural network.
Progressive Growing of GANs for improved Quality, Stability, and Variation
WHY?
Training GAN on high-resolution images is known to be difficult.
BERT: Pretraining of Deep Bidirectional Transformers for Language Understanding
WHY?
Former Transformer was unidirectional language model.
