William Petty, a doctor in Cromwell’s army in 1647, noted that ‘...we seechildren do delight in drums, pipes, fiddles, guns made of elder sticks, andbellowes noses, piped keys, etc., painting flags and ensigns with elder-berriesand corn poppy, making ships with paper, and setting even nut-shells aswimming, handling the tools of workmen as soon as they turn their backs, andtrying to work themselves’ (reported in the Harleian Miscellany, 1810).

Consider a toy model where we train an embedding of five features of varying importanceWhere “importance” is a scalar multiplier on mean squared error loss. in two dimensions, add a ReLU afterwards for filtering, and vary the sparsity of the features.

in reality pretty much everyone out there has some messiness in their graph and that's okay

Some details of my example were originally poorly chosen i.e. the example was constructed in a way that developer would probably have done a null check rather than a typeof comparison. I've addressed that now. My apologies to anyone who read this before-hand and thought the example seemed a bit too "fabricated".

ow we might accelerate the path to the Metaverse by a focus on desktop access by remote workers: Could it be that the Metaverse starts with people working together in virtual offices, and then staying around and connecting for various reasons outside of work? 

Granted it's a toy example using StringIO

A fun, language-less educational robot that teaches the concepts of coding. Arrange the command panels to guide the robot to the goal!