• Publications
  • Influence
Catastrophic Interference in Neural Embedding Models
  • 2
  • 1
Facial Emotion Detection Using Convolutional Neural Networks and Representational Autoencoder Units
TLDR
We use representational autoencoders to construct a unique representation of each emotion, while the second method is an 8-layer convolutional neural network (CNN). Expand
  • 27
  • PDF
Query-Key Normalization for Transformers
TLDR
We propose QKNorm, a normalization technique that modifies the attention mechanism to make the softmax function less prone to arbitrary saturation without sacrificing expressivity. Expand
  • 2
  • PDF
In-depth Question classification using Convolutional Neural Networks
Convolutional neural networks for computer vision are fairly intuitive. In a typical CNN used in image classification, the first layers learn edges, and the following layers learn some filters thatExpand