4 citations · 9 across the 12 of their papers we have counts for
Showing 2021 · cs.LGShow all
2 papers · 2 filters
cs.LG2021
Shared Visual Representations of Drawing for Communication: How do different biases affect human interpretability and intent?
Daniela Mihai, Jonathon Hare
We present an investigation into how representational losses can affect the drawings produced by artificial agents playing a communication game. Building upon recent advances, we s…
cs.LG2021
GhostShiftAddNet: More Features from Energy-Efficient Operations
Jia Bi, Jonathon Hare, Geoff V. Merrett
Deep convolutional neural networks (CNNs) are computationally and memory intensive. In CNNs, intensive multiplication can have resource implications that may challenge the ability…