resources
visualizations
presentations
lunch break
Distractions and amusements, with a sandwich and coffee.
Fonts + Design
Snellen Optotype Font with Upper and Lowercase characters
In the process of designing my Snellen Eye Chart typographical posters, I came across the Snellen font by Andrew Howlett. I wasn't happy with all the letters, so I made attempts at giving the font an update.
Not being a font designer, I will likely get myself into trouble.
snellen chart posters
While making my Snellen chart series, I entered the rabbit hole of optotype fonts ... and I can't get out!
buy artwork
buy artwork
The charts don't necessarily use the latest version of my Snellen font design, which fluctuates as my mood about some of the letters changes.
optotype fonts
The optotype requirement is that letters be designed on a 5 × 5 grid, and have constant stroke width. This means that both lower and upper case letters need to share the grid and stroke. To stay compatible with the eyechart paradigm, letters should be as obvious as possible.
Lorrie Frear's article What are Optotypes? Eye Charts in Focus is a great read about optotypes and eye charts.
Snellen Optotype Letter Design
uppercase
The uppercase letter design uses Herman Snellen's original chart as inspiration.
I have modified the design by Andrew Howlett (see below) for some letters. All the changes are relatively minor: more serifs and consistent stroke width for bars on R and K.
lowercase
The lowercase characters should be considered experimental.
The progress of my redesign is shown below. I would greatly appreciate feedback and suggestions!
Download Snellen Optotype Font
The distribution contains both Andrew's version and my redesign.
v7.0 6-mar-2017 — Download Snellen optotype font
version 7 — 6 Feb 2017
Fixed g and e. Thanks to Makeesha Fisher for suggestions.
version 6 — 5 Feb 2017
Adjusted serifs on f, j, l, o, t to extend the full width of the grid. Added a lot more symbols.
version 5 — 4 Feb 2017
Added lowercase, digits and symbols.
version 4 — 23 Feb 2017
Adding digits.
version 3 — 22 Feb 2017
I'm exploring the lowercase characters. I don't know what I want to do with them. Make this into a more standard font in which lowercase letters are smaller, so that letters can fit their roles clearly when text is set in sentence case, or fill out the full optotype grid.
version 2 — 22 Feb 2017
Flushed out some inconsistencies in the uppercase characters. Added serifs to more letters.
Now all the letters occuppy the full 5 × 5 grid, including the I, whose serifs were widened to allow this. While this new uppercase I isn't as pretty as the old one, it makes the entire typeface more consistent to its optotype roots.
Still struggling with the G. In the original version, the descending stroke was cut off in the middle of a grid, which I didn't like.
The S has been fixed—thanks to Elanor Lutz for feedback.
I've color coded the characters slightly differently, drawing attention to ones that I feel need more thought.
The lowercase characters aren't color coded (yet) because ... most of them need help. Primarily, I'm vacillating between making them fill the full size of the 5 × 5 square, just like the uppercase characters, and keeping them confined to a 4 × 4 square, which incurs loss of legibility. If I make the letters the same size, it will be impossible to distinguish lowercase and uppercase characters some cases (e.g. c, i). Perhaps this is desired?
version 1 — 22 Feb 2017
First attempt at lowercase characters.
news + thoughts
Statistics vs Machine Learning
We conclude our series on Machine Learning with a comparison of two approaches: classical statistical inference and machine learning. The boundary between them is subject to debate, but important generalizations can be made.Inference creates a mathematical model of the datageneration process to formalize understanding or test a hypothesis about how the system behaves. Prediction aims at forecasting unobserved outcomes or future behavior. Typically we want to do both and know how biological processes work and what will happen next. Inference and ML are complementary in pointing us to biologically meaningful conclusions.
Statistics asks us to choose a model that incorporates our knowledge of the system, and ML requires us to choose a predictive algorithm by relying on its empirical capabilities. Justification for an inference model typically rests on whether we feel it adequately captures the essence of the system. The choice of pattern-learning algorithms often depends on measures of past performance in similar scenarios.
Bzdok, D., Krzywinski, M. & Altman, N. (2018) Points of Significance: Statistics vs machine learning. Nature Methods 15:233–234.
Background reading
Bzdok, D., Krzywinski, M. & Altman, N. (2017) Points of Significance: Machine learning: a primer. Nature Methods 14:1119–1120.
Bzdok, D., Krzywinski, M. & Altman, N. (2017) Points of Significance: Machine learning: supervised methods. Nature Methods 15:5–6.
Happy 2018 `\pi` Day—Boonies, burbs and boutiques of `\pi`
Celebrate `\pi` Day (March 14th) and go to brand new places. Together with Jake Lever, this year we shrink the world and play with road maps.
Streets are seamlessly streets from across the world. Finally, a halva shop on the same block!
Intriguing and personal patterns of urban development for each city appear in the Boonies, Burbs and Boutiques series.
No color—just lines. Lines from Marrakesh, Prague, Istanbul, Nice and other destinations for the mind and the heart.
The art is featured in the Pi City on the Scientific American SA Visual blog.
Check out art from previous years: 2013 `\pi` Day and 2014 `\pi` Day, 2015 `\pi` Day, 2016 `\pi` Day and 2017 `\pi` Day.
Machine learning: supervised methods (SVM & kNN)
Supervised learning algorithms extract general principles from observed examples guided by a specific prediction objective.We examine two very common supervised machine learning methods: linear support vector machines (SVM) and k-nearest neighbors (kNN).
SVM is often less computationally demanding than kNN and is easier to interpret, but it can identify only a limited set of patterns. On the other hand, kNN can find very complex patterns, but its output is more challenging to interpret.
We illustrate SVM using a data set in which points fall into two categories, which are separated in SVM by a straight line "margin". SVM can be tuned using a parameter that influences the width and location of the margin, permitting points to fall within the margin or on the wrong side of the margin. We then show how kNN relaxes explicit boundary definitions, such as the straight line in SVM, and how kNN too can be tuned to create more robust classification.
Bzdok, D., Krzywinski, M. & Altman, N. (2018) Points of Significance: Machine learning: a primer. Nature Methods 15:5–6.
Background reading
Bzdok, D., Krzywinski, M. & Altman, N. (2017) Points of Significance: Machine learning: a primer. Nature Methods 14:1119–1120.
Human Versus Machine
Balancing subjective design with objective optimization.In a Nature graphics blog article, I present my process behind designing the stark black-and-white Nature 10 cover.
Nature 10, 18 December 2017
Machine learning: a primer
Machine learning extracts patterns from data without explicit instructions.In this primer, we focus on essential ML principles— a modeling strategy to let the data speak for themselves, to the extent possible.
The benefits of ML arise from its use of a large number of tuning parameters or weights, which control the algorithm’s complexity and are estimated from the data using numerical optimization. Often ML algorithms are motivated by heuristics such as models of interacting neurons or natural evolution—even if the underlying mechanism of the biological system being studied is substantially different. The utility of ML algorithms is typically assessed empirically by how well extracted patterns generalize to new observations.
We present a data scenario in which we fit to a model with 5 predictors using polynomials and show what to expect from ML when noise and sample size vary. We also demonstrate the consequences of excluding an important predictor or including a spurious one.
Bzdok, D., Krzywinski, M. & Altman, N. (2017) Points of Significance: Machine learning: a primer. Nature Methods 14:1119–1120.