Show newer

Go to sleep is the "Turn it off and back on again." tech support for the human brain.

@CanadianPaintings
There is happiness & joy throughout Mother Nature
Mark Anthony Jacobson - Ojibwe
2016

(30/50)

Went to class and learnt that next week's class will be streamed online, so I can travel a couple days earlier for holiday.

Summary:

Class: 1

(29/50)

Barely got any sleep and forced myself to go class.

Summary:

Class: 1

Does anyone have any thoughts on managing their research data using SQL or similar? I'm rapidly entering the zone where I have many disparate CSV files with measurements for the same sample set, and thinking a hierarchical approach may be useful here to collate data usefully. Would have to be usable within R, but otherwise I'm open. I'm looking at Apache Arrow, but I have no idea whether this is the right tool for this job.

(27/50)

Jumping back to the basics and writing up notes on $\sigma$-algebras.

Summary:

Notes: 1

This mind-bending timelapse with the Milky Way stabilized shows the Earth is spinning through space.

Credit: Eric Brummel
instagram.com/brummelphoto

#photography #milkyway #space

(25/50)

Off to bring tutorium notes into digital format in WTI.

Summary:

Notes: 1

(23/50)

Just one of those days that one is too busy to do much more.

Summary:

Quiz: 1

(22/50)

Had a situation today where I could use the Kullback–Leibler divergence to compare differences of bus routes that have potential alternate routes. Though it might be a bit overkill.

Summary:

Quiz: 1

(21/50)

Continued and finished the homework from day 19.

The one problem dealt with showing that the Kullback–Leibler divergence is greater equal to zero with using the Jensen's inequality.

The other problem dealt with showing the moment-generating function for the gamma distribution.

Summary:

Homework: 2

(20/50)

Dealt with the step function in class. The image defines a step function. To my understanding it is right continuous, so wouldn't it be an over estimate for functions that are $f'(x) < 0$ and thus in such a case the ceiling function would be better? Or does it not matter?

Summary:

Class: 2

A question:

Let's say we have a symmetric distribution around /(x=\alpha/). In this case is the expected value /(/mathbb{E}(X)=\alpha/)?

If the symmetric distribution is /(f(x)/), then what would be the median? Is it /(f(/alpha)/) or is it just /(/alpha/).

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.