Christopher Bryant

Thanks for the detailed review! I believe your intuition is correct. The indices p and q in the section you quoted do refer to the units of a specific layer...

It's been about a year and a half since I took this course, so my memory of Andrew's approach is a little hazy. But I'll try my best to remember...

∂J/∂Θ is a function of the network parameters and the network inputs in the same way that the derivative of an arbitrary function f(x) depends on both what f looks...

No worries! I'm happy to help. Though both _p_ and _k_ both refer to the same layer, at any given time, _p_ and _k_ could be referring to two different...

I believe that the sum is over _j_ (the index which tells you which element in the row is being referred to), for all elements where _r_ = 1. The...

For me, I think the ideal experience would be for every item to have an easily-visible single number score (maybe the lower bound of the 95% confidence interval) which re-orders...

Interesting! I had no idea. I think you might be right then that it’s probably better to use the average star rating rather than the raw star distribution.

**Note:** On hover over each element with class "a-icon a-icon-popover", a new div is created (and persisted in browser) with class "a-popover a-popover-no-header a-declarative a-arrow-bottom". Buried deep within this div...

Good point. 1. I think this may still be worth looking into since I'm not sure how sound the statistics are if we don't have access to the full star...

@aeciorc I added a function `evaluateAverageRating(avgRating, numRatings)` to the `confidence_interval.js` file under the shared directory, but I'm not familiar enough with web development to understand how to make that function...