Tag: principles

Guidelines for Ethical AI

As AI systems become more prevalent in society, we face bigger and tougher societal challenges. Given many of these challenges have not been faced before, practitioners will face scenarios that will require dealing with hard ethical and societal questions.
There has been a large amount of content published which attempts to address these issues through “Principles”, “Ethics Frameworks”, “Checklists” and beyond. However navigating the broad number of resources is not easy.
This repository aims to simplify this by mapping the ecosystem of guidelines, principles, codes of ethics, standards and regulation being put in place around artificial intelligence.
github.com/EthicalML/awesome-artificial-intelligence-guidelines/

🔍 High Level Frameworks & Principles	🔏 Processes & Checklists	🔨 Interactive & Practical Tools
📜 Industry standards initiatives	📚 Online Courses	🤖 Research and Industry Newsletters
⚔ Regulation and Policy

Links to Awesome Artificial Intelligence Guidelines

This overview of ethical guidelines for Artificial Intelligence is by the same author of the repository of Machine Learning production resources shared earlier this year.

Google’s Responsible AI Practices

As a company that uses a lot of automation, optimization, and machine learning in their day-to-day business, Google is set on developing AI in a socially responsible way.

Fortunately for us, Google decided to share their principles and best practices for us to read.

Google’s Objectives for AI applications

The details behind the seven objectives below you can find here.

Be socially beneficial.
Avoid creating or reinforcing unfair bias.
Be built and tested for safety.
Be accountable to people.
Incorporate privacy design principles.
Uphold high standards of scientific excellence.
Be made available for uses that accord with these principles.

Moreover, there are several AI technologies that Google will not build:

Google’s best practices for Responsible AI

For the details behind these six best practices, read more here.

Use a Human-centered approach (see also here)
Identify multiple metrics to assess training and monitoring
When possible, directly examine your raw data
Understand the limitations of your dataset and model
Test, Test, Test,
Continue to monitor and update the system after deployment

Best practices for writing good, clean JavaScript code

Robert Martin’s book Clean Code has been on my to-read list for months now. Browsing the web, I stumbled across this repository of where Ryan McDermott applied the book’s principles to JavaScript. Basically, he made a guide to producing readable, reusable, and refactorable software code in JavaScript.

Although Ryan’s good and bad code examples are written in JavaScript, the basic principles (i.e. “Uncle Bob”‘s Clean Code principles) are applicable to any programming language. At least, I recognize many of the best practices I’d teach data science students in R or Python.

Find the JavaScript best practices github repo here: github.com/ryanmcdermott/clean-code-javascript

Knowing these won’t immediately make you a better software developer, and working with them for many years doesn’t mean you won’t make mistakes. Every piece of code starts as a first draft, like wet clay getting shaped into its final form. Finally, we chisel away the imperfections when we review it with our peers. Don’t beat yourself up for first drafts that need improvement. Beat up the code instead!
Ryan McDermott via clean-code-javascript

Screenshots from the repo:

Ryan McDermott’s github of clean JavaScript code

Here are some of the principles listed, with hyperlinks:

But there are many, many more! Have a look at the original repo.

17 Principles of (Unix) Software Design

I came across this 1999-2003 e-book by Eric Raymond, on the Art of Unix Programming. It contains several relevant overviews of the basic principles behind the Unix philosophy, which are probably useful for anybody working in hardware, software, or other algoritmic design.

First up, is a great list of 17 design rules, explained in more detail in the original article:

Rule of Modularity: Write simple parts connected by clean interfaces.
Rule of Clarity: Clarity is better than cleverness.
Rule of Composition: Design programs to be connected to other programs.
Rule of Separation: Separate policy from mechanism; separate interfaces from engines.
Rule of Simplicity: Design for simplicity; add complexity only where you must.
Rule of Parsimony: Write a big program only when it is clear by demonstration that nothing else will do.
Rule of Transparency: Design for visibility to make inspection and debugging easier.
Rule of Robustness: Robustness is the child of transparency and simplicity.
Rule of Representation: Fold knowledge into data so program logic can be stupid and robust.
Rule of Least Surprise: In interface design, always do the least surprising thing.
Rule of Silence: When a program has nothing surprising to say, it should say nothing.
Rule of Repair: When you must fail, fail noisily and as soon as possible.
Rule of Economy: Programmer time is expensive; conserve it in preference to machine time.
Rule of Generation: Avoid hand-hacking; write programs to write programs when you can.
Rule of Optimization: Prototype before polishing. Get it working before you optimize it.
Rule of Diversity: Distrust all claims for “one true way”.
Rule of Extensibility: Design for the future, because it will be here sooner than you think.

Moreover, the book contains a shortlist of some of the philosophical principles behind Unix (and software design in general):

Everything that can be a source- and destination-independent filter should be one.
Data streams should if at all possible be textual (so they can be viewed and filtered with standard tools).
Database layouts and application protocols should if at all possible be textual (human-readable and human-editable).
Complex front ends (user interfaces) should be cleanly separated from complex back ends.
Whenever possible, prototype in an interpreted language before coding C.
Mixing languages is better than writing everything in one, if and only if using only that one is likely to overcomplicate the program.
Be generous in what you accept, rigorous in what you emit.
When filtering, never throw away information you don’t need to.
Small is beautiful. Write programs that do as little as is consistent with getting the job done.

If you want to read the real book, or if you just want to support the original author, you can buy the book here: