643 citations · 2.1k across the 8 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.NE2017★ 546 cited
A Neural Representation of Sketch Drawings
David Ha, Douglas Eck
We present sketch-rnn, a recurrent neural network (RNN) able to construct stroke-based drawings of common objects. The model is trained on thousands of crude human-drawn images rep…
cs.NE2017★ 643 cited
PathNet: Evolution Channels Gradient Descent in Super Neural Networks
Chrisantha Fernando, Dylan Banarse, Charles Blundell +5
For artificial general intelligence (AGI) it would be efficient if multiple users trained the same giant neural network, permitting parameter reuse, without catastrophic forgetting…