Experiments in Handwriting with a Neural Network

By Shan Carter, David R Ha, I. Johnson, Christopher Olah. 2016

23 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Recurrent World Models Facilitate Policy Evolution (2018, methodology): “MDN-RNN similar to the one used in [6, 24, 28] (right).”
Solving Rubik's Cube with a Robot Hand (2019, methodology): “We used neural network interpretability techniques [13, 75] to visualize policy recurrent states during a rollout.”
Combining Design and Performance in a Data Visualization Management System (2017, methodology): “Using off the shelf models [12], the model is 82% accurate at predicting the widget that the user will interact with in 200ms.”
Reinforcement Learning for Improving Agent Design (2018, background): “This approach may lead to useful applications in machine-learning-assisted design, in the spirit of [14, 15].”
Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers (2018, unknown): “Later, we will discuss the different visualization techniques and visual analytics systems that focus on neural network interpretability for embeddings [51], text [32], [40], [41], quantifying interpretability [29], and many different image-based techniques stemming from the AI communities [4], [10]”