Experiments in Handwriting with a Neural Network

This is incredible important research. There are fields in which adoption of ML techniques is dependent on it being explainable and inspectable to stakeholders, e.g. in certain health care, policy or finance applications.<p>There is work being done on explaining non-linear models, such as LIME [1], but much more is needed. At a recent d3 meetup the topic was discussed but we primarily noted its importance. Notes at [2].<p>[1] <a href="https:&#x2F;&#x2F;github.com&#x2F;marcotcr&#x2F;lime" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;marcotcr&#x2F;lime</a> [2] <a href="https:&#x2F;&#x2F;docs.google.com&#x2F;document&#x2F;d&#x2F;1o-DO65PEZShLuadyRd35PsTJ_XMi62Nhb1XOVQu2sUQ&#x2F;edit" rel="nofollow">https:&#x2F;&#x2F;docs.google.com&#x2F;document&#x2F;d&#x2F;1o-DO65PEZShLuadyRd35PsTJ...</a>

Me and the other authors of the post will be around if anyone has any questions.

In &quot;Examining the Internals of the Model&quot; it could be interesting to show an overview activation map that sums over the absolute activation of all the examples—to highlight which cells activate on all examples—and one that is colored by variance of activation across examples—to show which cells influence the character&#x2F;differences in writing.

Nice! Is it trained on Latin character-based hand writing only, or can it also predict other charactersets?

Quite interesting to see the inspection of the model.

We&#x27;re slowly coming to an era where everything can be easily forged.