2 papers
cs.CL2024
Position Information Emerges in Causal Transformers Without Positional Encodings via Similarity of Nearby Embeddings
Chunsheng Zuo, Pavel Guerzhoy, Michael Guerzhoy
Transformers with causal attention can solve tasks that require positional information without using positional encodings. In this work, we propose and investigate a new hypothesis…
cs.CV2020
Salient Facial Features from Humans and Deep Neural Networks
Shanmeng Sun, Wei Zhen Teoh, Michael Guerzhoy
In this work, we explore the features that are used by humans and by convolutional neural networks (ConvNets) to classify faces. We use Guided Backpropagation (GB) to visualize the…